Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3202 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.6129. Min Range: -8.6129
Max Act: 8.6129. Min Act: -0.1700
Data Index: 8422323 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6129. Min Range: -8.6129
Max Act: 8.3004. Min Act: -0.1700
Data Index: 6334407 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6129. Min Range: -8.6129
Max Act: 8.1754. Min Act: -0.1700
Data Index: 6147842 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6129. Min Range: -8.6129
Max Act: 8.1754. Min Act: -0.1700
Data Index: 2581112 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6129. Min Range: -8.6129
Max Act: 8.2379. Min Act: -0.1700
Data Index: 2525576 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6129. Min Range: -8.6129
Max Act: 8.1754. Min Act: -0.1700
Data Index: 2221033 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6129. Min Range: -8.6129
Max Act: 8.1129. Min Act: -0.1700
Data Index: 5765800 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6129. Min Range: -8.6129
Max Act: 8.1754. Min Act: -0.1700
Data Index: 6210975 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6129. Min Range: -8.6129
Max Act: 8.1754. Min Act: -0.1700
Data Index: 6493186 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6129. Min Range: -8.6129
Max Act: 8.1754. Min Act: -0.1700
Data Index: 2675494 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6129. Min Range: -8.6129
Max Act: 8.2379. Min Act: -0.1700
Data Index: 6156391 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6129. Min Range: -8.6129
Max Act: 8.1129. Min Act: -0.1700
Data Index: 4506585 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6129. Min Range: -8.6129
Max Act: 8.1129. Min Act: -0.1700
Data Index: 8193042 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6129. Min Range: -8.6129
Max Act: 8.1129. Min Act: -0.1700
Data Index: 1585187 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6129. Min Range: -8.6129
Max Act: 8.1129. Min Act: -0.1700
Data Index: 2831801 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6129. Min Range: -8.6129
Max Act: 8.1129. Min Act: -0.1700
Data Index: 7064166 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6129. Min Range: -8.6129
Max Act: 8.1129. Min Act: -0.1700
Data Index: 7925798 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6129. Min Range: -8.6129
Max Act: 8.1754. Min Act: -0.1700
Data Index: 7101266 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6129. Min Range: -8.6129
Max Act: 8.1129. Min Act: -0.1700
Data Index: 109 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6129. Min Range: -8.6129
Max Act: 8.1129. Min Act: -0.1700
Data Index: 4150328 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #19