Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4736 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4242. Min Range: -8.4242
Max Act: 8.4242. Min Act: -0.1700
Data Index: 4108864 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4242. Min Range: -8.4242
Max Act: 8.1742. Min Act: -0.1700
Data Index: 5429830 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4242. Min Range: -8.4242
Max Act: 8.1117. Min Act: -0.1700
Data Index: 3525002 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4242. Min Range: -8.4242
Max Act: 7.9867. Min Act: -0.1700
Data Index: 5875122 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4242. Min Range: -8.4242
Max Act: 7.9867. Min Act: -0.1700
Data Index: 784192 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4242. Min Range: -8.4242
Max Act: 7.8617. Min Act: -0.1700
Data Index: 2790121 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4242. Min Range: -8.4242
Max Act: 7.8617. Min Act: -0.1700
Data Index: 3412676 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4242. Min Range: -8.4242
Max Act: 7.8617. Min Act: -0.1700
Data Index: 5072404 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4242. Min Range: -8.4242
Max Act: 7.8617. Min Act: -0.1700
Data Index: 7640795 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4242. Min Range: -8.4242
Max Act: 7.7992. Min Act: -0.1700
Data Index: 4119598 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4242. Min Range: -8.4242
Max Act: 7.7992. Min Act: -0.1700
Data Index: 2511174 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4242. Min Range: -8.4242
Max Act: 7.7367. Min Act: -0.1700
Data Index: 7742167 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4242. Min Range: -8.4242
Max Act: 7.7367. Min Act: -0.1700
Data Index: 1976389 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4242. Min Range: -8.4242
Max Act: 7.7367. Min Act: -0.1700
Data Index: 3217673 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4242. Min Range: -8.4242
Max Act: 7.7367. Min Act: -0.1700
Data Index: 2849620 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4242. Min Range: -8.4242
Max Act: 7.7367. Min Act: -0.1700
Data Index: 5365349 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4242. Min Range: -8.4242
Max Act: 7.7367. Min Act: -0.1700
Data Index: 4031326 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4242. Min Range: -8.4242
Max Act: 7.6742. Min Act: -0.1700
Data Index: 2693792 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4242. Min Range: -8.4242
Max Act: 7.6742. Min Act: -0.1700
Data Index: 3331481 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4242. Min Range: -8.4242
Max Act: 7.6117. Min Act: -0.1700
Data Index: 2419438 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #19