Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3880 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3290. Min Range: -5.3290
Max Act: 5.3290. Min Act: -0.1700
Data Index: 3040470 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3290. Min Range: -5.3290
Max Act: 5.2352. Min Act: -0.1700
Data Index: 8587706 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3290. Min Range: -5.3290
Max Act: 5.2352. Min Act: -0.1700
Data Index: 5481916 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3290. Min Range: -5.3290
Max Act: 5.2040. Min Act: -0.1699
Data Index: 8683278 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3290. Min Range: -5.3290
Max Act: 5.2040. Min Act: -0.1700
Data Index: 3298824 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3290. Min Range: -5.3290
Max Act: 5.1415. Min Act: -0.1700
Data Index: 6379460 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3290. Min Range: -5.3290
Max Act: 5.1415. Min Act: -0.1700
Data Index: 2352458 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3290. Min Range: -5.3290
Max Act: 5.1102. Min Act: -0.1700
Data Index: 4280598 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3290. Min Range: -5.3290
Max Act: 5.1102. Min Act: -0.1700
Data Index: 7242562 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3290. Min Range: -5.3290
Max Act: 5.1102. Min Act: -0.1700
Data Index: 676539 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3290. Min Range: -5.3290
Max Act: 5.1102. Min Act: -0.1700
Data Index: 8535042 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3290. Min Range: -5.3290
Max Act: 5.0790. Min Act: -0.1700
Data Index: 7665680 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3290. Min Range: -5.3290
Max Act: 5.0790. Min Act: -0.1700
Data Index: 5880466 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3290. Min Range: -5.3290
Max Act: 5.0790. Min Act: -0.1699
Data Index: 6376555 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3290. Min Range: -5.3290
Max Act: 5.0790. Min Act: -0.1700
Data Index: 2638116 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3290. Min Range: -5.3290
Max Act: 5.0790. Min Act: -0.1700
Data Index: 1369628 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3290. Min Range: -5.3290
Max Act: 5.0477. Min Act: -0.1699
Data Index: 5962592 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3290. Min Range: -5.3290
Max Act: 5.0790. Min Act: -0.1700
Data Index: 5981239 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3290. Min Range: -5.3290
Max Act: 5.0477. Min Act: -0.1700
Data Index: 4170035 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3290. Min Range: -5.3290
Max Act: 5.0790. Min Act: -0.1700
Data Index: 573377 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #19