Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1087 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4940. Min Range: -6.4940
Max Act: 6.4940. Min Act: -0.1700
Data Index: 8601642 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4940. Min Range: -6.4940
Max Act: 6.4940. Min Act: -0.1700
Data Index: 3745966 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4940. Min Range: -6.4940
Max Act: 6.4628. Min Act: -0.1700
Data Index: 4503261 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4940. Min Range: -6.4940
Max Act: 6.4315. Min Act: -0.1700
Data Index: 7207692 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4940. Min Range: -6.4940
Max Act: 6.4003. Min Act: -0.1700
Data Index: 4850045 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4940. Min Range: -6.4940
Max Act: 6.4315. Min Act: -0.1700
Data Index: 1671780 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4940. Min Range: -6.4940
Max Act: 6.4315. Min Act: -0.1700
Data Index: 29748 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4940. Min Range: -6.4940
Max Act: 6.4003. Min Act: -0.1700
Data Index: 1514406 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4940. Min Range: -6.4940
Max Act: 6.4003. Min Act: -0.1700
Data Index: 8322133 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4940. Min Range: -6.4940
Max Act: 6.4003. Min Act: -0.1700
Data Index: 2010733 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4940. Min Range: -6.4940
Max Act: 6.4003. Min Act: -0.1700
Data Index: 7410468 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4940. Min Range: -6.4940
Max Act: 6.4003. Min Act: -0.1700
Data Index: 1095460 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4940. Min Range: -6.4940
Max Act: 6.4003. Min Act: -0.1700
Data Index: 8762047 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4940. Min Range: -6.4940
Max Act: 6.4003. Min Act: -0.1700
Data Index: 2241117 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4940. Min Range: -6.4940
Max Act: 6.4003. Min Act: -0.1700
Data Index: 6727305 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4940. Min Range: -6.4940
Max Act: 6.3690. Min Act: -0.1700
Data Index: 1588662 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4940. Min Range: -6.4940
Max Act: 6.3690. Min Act: -0.1700
Data Index: 4690662 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4940. Min Range: -6.4940
Max Act: 6.3690. Min Act: -0.1700
Data Index: 2111388 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4940. Min Range: -6.4940
Max Act: 6.3690. Min Act: -0.1700
Data Index: 3006925 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4940. Min Range: -6.4940
Max Act: 6.3378. Min Act: -0.1700
Data Index: 1097166 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #19