Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1753 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 14.2893. Min Range: -14.2893
Max Act: 14.2893. Min Act: -0.1700
Data Index: 1991175 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 14.2893. Min Range: -14.2893
Max Act: 13.9143. Min Act: -0.1700
Data Index: 6418515 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 14.2893. Min Range: -14.2893
Max Act: 13.5393. Min Act: -0.1700
Data Index: 8445376 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 14.2893. Min Range: -14.2893
Max Act: 13.3518. Min Act: -0.1700
Data Index: 3649079 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 14.2893. Min Range: -14.2893
Max Act: 13.2268. Min Act: -0.1700
Data Index: 6745820 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 14.2893. Min Range: -14.2893
Max Act: 13.2268. Min Act: -0.1700
Data Index: 4401801 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 14.2893. Min Range: -14.2893
Max Act: 13.1643. Min Act: -0.1700
Data Index: 3822456 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 14.2893. Min Range: -14.2893
Max Act: 13.1018. Min Act: -0.1700
Data Index: 4853298 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 14.2893. Min Range: -14.2893
Max Act: 13.1018. Min Act: -0.1700
Data Index: 88299 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 14.2893. Min Range: -14.2893
Max Act: 13.1018. Min Act: -0.1700
Data Index: 6553517 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 14.2893. Min Range: -14.2893
Max Act: 12.9143. Min Act: -0.1700
Data Index: 1462390 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 14.2893. Min Range: -14.2893
Max Act: 13.1018. Min Act: -0.1700
Data Index: 3893454 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 14.2893. Min Range: -14.2893
Max Act: 13.0393. Min Act: -0.1700
Data Index: 6745815 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 14.2893. Min Range: -14.2893
Max Act: 12.9143. Min Act: -0.1700
Data Index: 5760555 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 14.2893. Min Range: -14.2893
Max Act: 12.9768. Min Act: -0.1700
Data Index: 6924841 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 14.2893. Min Range: -14.2893
Max Act: 12.9143. Min Act: -0.1700
Data Index: 249277 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 14.2893. Min Range: -14.2893
Max Act: 12.8518. Min Act: -0.1700
Data Index: 4478317 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 14.2893. Min Range: -14.2893
Max Act: 12.7893. Min Act: -0.1700
Data Index: 3224814 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 14.2893. Min Range: -14.2893
Max Act: 12.8518. Min Act: -0.1700
Data Index: 907307 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 14.2893. Min Range: -14.2893
Max Act: 12.8518. Min Act: -0.1700
Data Index: 7117067 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #19