Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3996 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2382. Min Range: -7.2382
Max Act: 7.2382. Min Act: -0.1700
Data Index: 7909619 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2382. Min Range: -7.2382
Max Act: 7.1757. Min Act: -0.1700
Data Index: 391632 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2382. Min Range: -7.2382
Max Act: 7.1445. Min Act: -0.1700
Data Index: 4105302 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2382. Min Range: -7.2382
Max Act: 7.0195. Min Act: -0.1700
Data Index: 8470861 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2382. Min Range: -7.2382
Max Act: 7.0195. Min Act: -0.1700
Data Index: 5572243 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2382. Min Range: -7.2382
Max Act: 6.9257. Min Act: -0.1700
Data Index: 3637826 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2382. Min Range: -7.2382
Max Act: 6.8945. Min Act: -0.1700
Data Index: 6148852 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2382. Min Range: -7.2382
Max Act: 6.8945. Min Act: -0.1700
Data Index: 4403443 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2382. Min Range: -7.2382
Max Act: 6.8632. Min Act: -0.1700
Data Index: 2212646 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2382. Min Range: -7.2382
Max Act: 6.8632. Min Act: -0.1700
Data Index: 6666177 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2382. Min Range: -7.2382
Max Act: 6.8632. Min Act: -0.1700
Data Index: 3151354 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2382. Min Range: -7.2382
Max Act: 6.8320. Min Act: -0.1700
Data Index: 5993567 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2382. Min Range: -7.2382
Max Act: 6.8007. Min Act: -0.1700
Data Index: 999172 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2382. Min Range: -7.2382
Max Act: 6.8007. Min Act: -0.1700
Data Index: 1354064 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2382. Min Range: -7.2382
Max Act: 6.8007. Min Act: -0.1700
Data Index: 8299156 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2382. Min Range: -7.2382
Max Act: 6.8007. Min Act: -0.1700
Data Index: 6598557 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2382. Min Range: -7.2382
Max Act: 6.8007. Min Act: -0.1700
Data Index: 5505038 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2382. Min Range: -7.2382
Max Act: 6.7695. Min Act: -0.1700
Data Index: 3088157 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2382. Min Range: -7.2382
Max Act: 6.7695. Min Act: -0.1700
Data Index: 269855 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2382. Min Range: -7.2382
Max Act: 6.7695. Min Act: -0.1700
Data Index: 4547737 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #19