Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2891 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1223. Min Range: -8.1223
Max Act: 8.1223. Min Act: -0.1700
Data Index: 7472659 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1223. Min Range: -8.1223
Max Act: 7.7473. Min Act: -0.1700
Data Index: 828606 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1223. Min Range: -8.1223
Max Act: 7.5598. Min Act: -0.1700
Data Index: 7502744 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1223. Min Range: -8.1223
Max Act: 7.4661. Min Act: -0.1700
Data Index: 3203735 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1223. Min Range: -8.1223
Max Act: 7.4348. Min Act: -0.1700
Data Index: 6487586 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1223. Min Range: -8.1223
Max Act: 7.4036. Min Act: -0.1700
Data Index: 3356704 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1223. Min Range: -8.1223
Max Act: 7.3723. Min Act: -0.1700
Data Index: 7643833 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1223. Min Range: -8.1223
Max Act: 7.4036. Min Act: -0.1700
Data Index: 7365840 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1223. Min Range: -8.1223
Max Act: 7.3411. Min Act: -0.1700
Data Index: 7545092 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1223. Min Range: -8.1223
Max Act: 7.2786. Min Act: -0.1700
Data Index: 392556 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1223. Min Range: -8.1223
Max Act: 7.2473. Min Act: -0.1700
Data Index: 1270107 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1223. Min Range: -8.1223
Max Act: 7.2161. Min Act: -0.1700
Data Index: 8456792 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1223. Min Range: -8.1223
Max Act: 7.2161. Min Act: -0.1700
Data Index: 20928 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1223. Min Range: -8.1223
Max Act: 7.2473. Min Act: -0.1700
Data Index: 7055148 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1223. Min Range: -8.1223
Max Act: 7.2161. Min Act: -0.1700
Data Index: 4242617 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1223. Min Range: -8.1223
Max Act: 7.1536. Min Act: -0.1700
Data Index: 6132012 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1223. Min Range: -8.1223
Max Act: 7.1848. Min Act: -0.1700
Data Index: 233115 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1223. Min Range: -8.1223
Max Act: 7.1536. Min Act: -0.1700
Data Index: 8422303 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1223. Min Range: -8.1223
Max Act: 7.1848. Min Act: -0.1700
Data Index: 4375105 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1223. Min Range: -8.1223
Max Act: 7.1536. Min Act: -0.1700
Data Index: 3515385 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #19