Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3548 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2388. Min Range: -5.2388
Max Act: 5.2388. Min Act: -0.1700
Data Index: 7041552 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2388. Min Range: -5.2388
Max Act: 5.1763. Min Act: -0.1700
Data Index: 7479953 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2388. Min Range: -5.2388
Max Act: 5.1138. Min Act: -0.1700
Data Index: 530975 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2388. Min Range: -5.2388
Max Act: 5.1138. Min Act: -0.1700
Data Index: 3170152 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2388. Min Range: -5.2388
Max Act: 5.1138. Min Act: -0.1700
Data Index: 6660732 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2388. Min Range: -5.2388
Max Act: 5.1138. Min Act: -0.1700
Data Index: 503064 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2388. Min Range: -5.2388
Max Act: 5.1138. Min Act: -0.1700
Data Index: 1872610 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2388. Min Range: -5.2388
Max Act: 5.0826. Min Act: -0.1700
Data Index: 5407470 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2388. Min Range: -5.2388
Max Act: 5.0826. Min Act: -0.1700
Data Index: 983269 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2388. Min Range: -5.2388
Max Act: 5.0826. Min Act: -0.1700
Data Index: 7245014 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2388. Min Range: -5.2388
Max Act: 5.0513. Min Act: -0.1700
Data Index: 8048870 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2388. Min Range: -5.2388
Max Act: 5.0826. Min Act: -0.1700
Data Index: 5116909 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2388. Min Range: -5.2388
Max Act: 5.0513. Min Act: -0.1700
Data Index: 5451859 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2388. Min Range: -5.2388
Max Act: 5.0201. Min Act: -0.1700
Data Index: 7303997 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2388. Min Range: -5.2388
Max Act: 5.0201. Min Act: -0.1700
Data Index: 4269187 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2388. Min Range: -5.2388
Max Act: 5.0201. Min Act: -0.1700
Data Index: 3292984 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2388. Min Range: -5.2388
Max Act: 5.0201. Min Act: -0.1700
Data Index: 2894982 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2388. Min Range: -5.2388
Max Act: 5.0201. Min Act: -0.1700
Data Index: 3597988 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2388. Min Range: -5.2388
Max Act: 5.0201. Min Act: -0.1700
Data Index: 6193249 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2388. Min Range: -5.2388
Max Act: 5.0201. Min Act: -0.1700
Data Index: 4886582 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #19