Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1078 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.8204. Min Range: -3.8204
Max Act: 3.8204. Min Act: -0.1700
Data Index: 1086612 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8204. Min Range: -3.8204
Max Act: 3.7579. Min Act: -0.1700
Data Index: 107251 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8204. Min Range: -3.8204
Max Act: 3.7579. Min Act: -0.1700
Data Index: 3982293 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8204. Min Range: -3.8204
Max Act: 3.7266. Min Act: -0.1700
Data Index: 6601118 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8204. Min Range: -3.8204
Max Act: 3.7110. Min Act: -0.1700
Data Index: 5198112 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8204. Min Range: -3.8204
Max Act: 3.6797. Min Act: -0.1700
Data Index: 18817 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8204. Min Range: -3.8204
Max Act: 3.6797. Min Act: -0.1700
Data Index: 8636060 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8204. Min Range: -3.8204
Max Act: 3.6484. Min Act: -0.1700
Data Index: 4362930 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8204. Min Range: -3.8204
Max Act: 3.6640. Min Act: -0.1700
Data Index: 5567051 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8204. Min Range: -3.8204
Max Act: 3.6014. Min Act: -0.1700
Data Index: 2392684 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8204. Min Range: -3.8204
Max Act: 3.5858. Min Act: -0.1700
Data Index: 1402248 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8204. Min Range: -3.8204
Max Act: 3.6014. Min Act: -0.1700
Data Index: 5535408 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8204. Min Range: -3.8204
Max Act: 3.5545. Min Act: -0.1700
Data Index: 1546488 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8204. Min Range: -3.8204
Max Act: 3.5858. Min Act: -0.1700
Data Index: 5891737 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8204. Min Range: -3.8204
Max Act: 3.5858. Min Act: -0.1700
Data Index: 5693052 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8204. Min Range: -3.8204
Max Act: 3.5232. Min Act: -0.1700
Data Index: 3974809 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8204. Min Range: -3.8204
Max Act: 3.5232. Min Act: -0.1700
Data Index: 823467 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8204. Min Range: -3.8204
Max Act: 3.5388. Min Act: -0.1700
Data Index: 4761604 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8204. Min Range: -3.8204
Max Act: 3.5545. Min Act: -0.1700
Data Index: 417806 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8204. Min Range: -3.8204
Max Act: 3.4918. Min Act: -0.1700
Data Index: 6128856 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #19