Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 408 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8932. Min Range: -5.8932
Max Act: 5.8932. Min Act: -0.1700
Data Index: 3854510 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8932. Min Range: -5.8932
Max Act: 5.8620. Min Act: -0.1700
Data Index: 1575896 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8932. Min Range: -5.8932
Max Act: 5.7995. Min Act: -0.1700
Data Index: 8739100 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8932. Min Range: -5.8932
Max Act: 5.7995. Min Act: -0.1700
Data Index: 711743 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8932. Min Range: -5.8932
Max Act: 5.6432. Min Act: -0.1700
Data Index: 6484949 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8932. Min Range: -5.8932
Max Act: 5.6432. Min Act: -0.1700
Data Index: 7612297 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8932. Min Range: -5.8932
Max Act: 5.5495. Min Act: -0.1700
Data Index: 8039159 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8932. Min Range: -5.8932
Max Act: 5.5182. Min Act: -0.1700
Data Index: 3879001 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8932. Min Range: -5.8932
Max Act: 5.4870. Min Act: -0.1700
Data Index: 3879002 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8932. Min Range: -5.8932
Max Act: 5.4557. Min Act: -0.1700
Data Index: 5632247 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8932. Min Range: -5.8932
Max Act: 5.4557. Min Act: -0.1700
Data Index: 5385790 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8932. Min Range: -5.8932
Max Act: 5.4245. Min Act: -0.1700
Data Index: 8495333 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8932. Min Range: -5.8932
Max Act: 5.4245. Min Act: -0.1700
Data Index: 4060648 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8932. Min Range: -5.8932
Max Act: 5.4245. Min Act: -0.1700
Data Index: 116845 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8932. Min Range: -5.8932
Max Act: 5.4245. Min Act: -0.1700
Data Index: 8373514 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8932. Min Range: -5.8932
Max Act: 5.3932. Min Act: -0.1700
Data Index: 2028953 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8932. Min Range: -5.8932
Max Act: 5.3932. Min Act: -0.1700
Data Index: 8389663 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8932. Min Range: -5.8932
Max Act: 5.3932. Min Act: -0.1700
Data Index: 3214279 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8932. Min Range: -5.8932
Max Act: 5.3620. Min Act: -0.1700
Data Index: 7103163 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8932. Min Range: -5.8932
Max Act: 5.3620. Min Act: -0.1700
Data Index: 1860258 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #19