Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3150 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.8777. Min Range: -9.8777
Max Act: 9.8777. Min Act: -0.1700
Data Index: 5503491 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.8777. Min Range: -9.8777
Max Act: 9.8152. Min Act: -0.1700
Data Index: 67404 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.8777. Min Range: -9.8777
Max Act: 9.8152. Min Act: -0.1700
Data Index: 2782501 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.8777. Min Range: -9.8777
Max Act: 9.7527. Min Act: -0.1700
Data Index: 1277673 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.8777. Min Range: -9.8777
Max Act: 9.7527. Min Act: -0.1700
Data Index: 1261243 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.8777. Min Range: -9.8777
Max Act: 9.7527. Min Act: -0.1700
Data Index: 4161469 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.8777. Min Range: -9.8777
Max Act: 9.7527. Min Act: -0.1700
Data Index: 1873889 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.8777. Min Range: -9.8777
Max Act: 9.6902. Min Act: -0.1700
Data Index: 3633103 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.8777. Min Range: -9.8777
Max Act: 9.6277. Min Act: -0.1700
Data Index: 6930754 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.8777. Min Range: -9.8777
Max Act: 9.6277. Min Act: -0.1700
Data Index: 4875411 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.8777. Min Range: -9.8777
Max Act: 9.6277. Min Act: -0.1700
Data Index: 4739459 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.8777. Min Range: -9.8777
Max Act: 9.6277. Min Act: -0.1700
Data Index: 7149151 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.8777. Min Range: -9.8777
Max Act: 9.6277. Min Act: -0.1700
Data Index: 2222759 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.8777. Min Range: -9.8777
Max Act: 9.6277. Min Act: -0.1700
Data Index: 295774 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.8777. Min Range: -9.8777
Max Act: 9.6277. Min Act: -0.1700
Data Index: 8305765 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.8777. Min Range: -9.8777
Max Act: 9.5652. Min Act: -0.1700
Data Index: 2070174 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.8777. Min Range: -9.8777
Max Act: 9.5652. Min Act: -0.1700
Data Index: 3868694 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.8777. Min Range: -9.8777
Max Act: 9.5652. Min Act: -0.1700
Data Index: 6058253 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.8777. Min Range: -9.8777
Max Act: 9.5652. Min Act: -0.1700
Data Index: 4815421 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.8777. Min Range: -9.8777
Max Act: 9.5027. Min Act: -0.1700
Data Index: 4321639 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #19