Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 525 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2098. Min Range: -5.2098
Max Act: 5.2098. Min Act: -0.1700
Data Index: 8692517 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2098. Min Range: -5.2098
Max Act: 4.8035. Min Act: -0.1700
Data Index: 2527356 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2098. Min Range: -5.2098
Max Act: 4.7098. Min Act: -0.1700
Data Index: 3889662 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2098. Min Range: -5.2098
Max Act: 4.5848. Min Act: -0.1700
Data Index: 5592370 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2098. Min Range: -5.2098
Max Act: 4.5848. Min Act: -0.1700
Data Index: 6674944 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2098. Min Range: -5.2098
Max Act: 4.5535. Min Act: -0.1700
Data Index: 1361612 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2098. Min Range: -5.2098
Max Act: 4.5535. Min Act: -0.1700
Data Index: 7249438 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2098. Min Range: -5.2098
Max Act: 4.5535. Min Act: -0.1700
Data Index: 7658745 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2098. Min Range: -5.2098
Max Act: 4.5223. Min Act: -0.1700
Data Index: 4949374 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2098. Min Range: -5.2098
Max Act: 4.5223. Min Act: -0.1700
Data Index: 5340568 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2098. Min Range: -5.2098
Max Act: 4.4910. Min Act: -0.1700
Data Index: 4877360 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2098. Min Range: -5.2098
Max Act: 4.4598. Min Act: -0.1700
Data Index: 1042096 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2098. Min Range: -5.2098
Max Act: 4.4598. Min Act: -0.1700
Data Index: 374771 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2098. Min Range: -5.2098
Max Act: 4.4598. Min Act: -0.1700
Data Index: 5058190 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2098. Min Range: -5.2098
Max Act: 4.4285. Min Act: -0.1700
Data Index: 5498230 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2098. Min Range: -5.2098
Max Act: 4.4598. Min Act: -0.1700
Data Index: 5927632 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2098. Min Range: -5.2098
Max Act: 4.4285. Min Act: -0.1700
Data Index: 4854081 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2098. Min Range: -5.2098
Max Act: 4.4285. Min Act: -0.1700
Data Index: 6039207 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2098. Min Range: -5.2098
Max Act: 4.4285. Min Act: -0.1700
Data Index: 3705658 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2098. Min Range: -5.2098
Max Act: 4.3973. Min Act: -0.1700
Data Index: 2531842 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #19