Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4470 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2445. Min Range: -7.2445
Max Act: 7.2445. Min Act: -0.1700
Data Index: 1075248 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2445. Min Range: -7.2445
Max Act: 7.1820. Min Act: -0.1700
Data Index: 4683140 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2445. Min Range: -7.2445
Max Act: 7.0882. Min Act: -0.1700
Data Index: 7439947 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2445. Min Range: -7.2445
Max Act: 7.0257. Min Act: -0.1700
Data Index: 5686664 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2445. Min Range: -7.2445
Max Act: 6.9945. Min Act: -0.1700
Data Index: 6082113 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2445. Min Range: -7.2445
Max Act: 6.9945. Min Act: -0.1700
Data Index: 88391 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2445. Min Range: -7.2445
Max Act: 6.9632. Min Act: -0.1700
Data Index: 7532169 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2445. Min Range: -7.2445
Max Act: 6.9007. Min Act: -0.1700
Data Index: 2905120 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2445. Min Range: -7.2445
Max Act: 6.9007. Min Act: -0.1700
Data Index: 5885992 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2445. Min Range: -7.2445
Max Act: 6.8695. Min Act: -0.1700
Data Index: 7047198 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2445. Min Range: -7.2445
Max Act: 6.9007. Min Act: -0.1700
Data Index: 3998045 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2445. Min Range: -7.2445
Max Act: 6.8695. Min Act: -0.1700
Data Index: 8796722 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2445. Min Range: -7.2445
Max Act: 6.8382. Min Act: -0.1700
Data Index: 298194 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2445. Min Range: -7.2445
Max Act: 6.8382. Min Act: -0.1700
Data Index: 6558532 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2445. Min Range: -7.2445
Max Act: 6.8382. Min Act: -0.1700
Data Index: 3164701 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2445. Min Range: -7.2445
Max Act: 6.8070. Min Act: -0.1700
Data Index: 3164703 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2445. Min Range: -7.2445
Max Act: 6.8382. Min Act: -0.1700
Data Index: 396428 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2445. Min Range: -7.2445
Max Act: 6.8070. Min Act: -0.1700
Data Index: 4540336 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2445. Min Range: -7.2445
Max Act: 6.7757. Min Act: -0.1700
Data Index: 2269797 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2445. Min Range: -7.2445
Max Act: 6.8070. Min Act: -0.1700
Data Index: 396426 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #19