Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4889 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6122. Min Range: -7.6122
Max Act: 7.6122. Min Act: -0.1700
Data Index: 3124345 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6122. Min Range: -7.6122
Max Act: 7.5497. Min Act: -0.1700
Data Index: 4885375 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6122. Min Range: -7.6122
Max Act: 7.5185. Min Act: -0.1700
Data Index: 1366693 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6122. Min Range: -7.6122
Max Act: 7.5185. Min Act: -0.1700
Data Index: 4422334 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6122. Min Range: -7.6122
Max Act: 7.5185. Min Act: -0.1700
Data Index: 4422342 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6122. Min Range: -7.6122
Max Act: 7.5185. Min Act: -0.1700
Data Index: 4851047 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6122. Min Range: -7.6122
Max Act: 7.4247. Min Act: -0.1700
Data Index: 7818280 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6122. Min Range: -7.6122
Max Act: 7.3935. Min Act: -0.1700
Data Index: 4522046 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6122. Min Range: -7.6122
Max Act: 7.3310. Min Act: -0.1700
Data Index: 5769757 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6122. Min Range: -7.6122
Max Act: 7.2997. Min Act: -0.1700
Data Index: 557364 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6122. Min Range: -7.6122
Max Act: 7.2997. Min Act: -0.1700
Data Index: 6042604 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6122. Min Range: -7.6122
Max Act: 7.2060. Min Act: -0.1700
Data Index: 8808187 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6122. Min Range: -7.6122
Max Act: 7.1747. Min Act: -0.1700
Data Index: 3045530 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6122. Min Range: -7.6122
Max Act: 7.2060. Min Act: -0.1700
Data Index: 4885374 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6122. Min Range: -7.6122
Max Act: 7.1747. Min Act: -0.1700
Data Index: 1257991 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6122. Min Range: -7.6122
Max Act: 7.1122. Min Act: -0.1700
Data Index: 4492143 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6122. Min Range: -7.6122
Max Act: 7.1122. Min Act: -0.1700
Data Index: 1232810 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6122. Min Range: -7.6122
Max Act: 7.1122. Min Act: -0.1700
Data Index: 871475 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6122. Min Range: -7.6122
Max Act: 7.1122. Min Act: -0.1700
Data Index: 8486324 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6122. Min Range: -7.6122
Max Act: 7.1122. Min Act: -0.1700
Data Index: 2514462 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #19