Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4815 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4348. Min Range: -6.4348
Max Act: 6.4348. Min Act: -0.1700
Data Index: 7968458 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4348. Min Range: -6.4348
Max Act: 6.1223. Min Act: -0.1700
Data Index: 8276692 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4348. Min Range: -6.4348
Max Act: 6.0911. Min Act: -0.1699
Data Index: 7217987 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4348. Min Range: -6.4348
Max Act: 5.9973. Min Act: -0.1700
Data Index: 947847 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4348. Min Range: -6.4348
Max Act: 5.9973. Min Act: -0.1695
Data Index: 4580717 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4348. Min Range: -6.4348
Max Act: 5.9661. Min Act: -0.1700
Data Index: 2895003 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4348. Min Range: -6.4348
Max Act: 5.9348. Min Act: -0.1700
Data Index: 2252430 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4348. Min Range: -6.4348
Max Act: 5.9348. Min Act: -0.1700
Data Index: 8005952 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4348. Min Range: -6.4348
Max Act: 5.9036. Min Act: -0.1695
Data Index: 2240348 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4348. Min Range: -6.4348
Max Act: 5.9036. Min Act: -0.1699
Data Index: 4966600 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4348. Min Range: -6.4348
Max Act: 5.8411. Min Act: -0.1694
Data Index: 7205841 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4348. Min Range: -6.4348
Max Act: 5.8723. Min Act: -0.1699
Data Index: 6318834 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4348. Min Range: -6.4348
Max Act: 5.8723. Min Act: -0.1700
Data Index: 416799 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4348. Min Range: -6.4348
Max Act: 5.8411. Min Act: -0.1700
Data Index: 667088 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4348. Min Range: -6.4348
Max Act: 5.9036. Min Act: -0.1700
Data Index: 7893488 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4348. Min Range: -6.4348
Max Act: 5.8723. Min Act: -0.1685
Data Index: 8626820 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4348. Min Range: -6.4348
Max Act: 5.8098. Min Act: -0.1699
Data Index: 12400 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4348. Min Range: -6.4348
Max Act: 5.8098. Min Act: -0.1700
Data Index: 7173456 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4348. Min Range: -6.4348
Max Act: 5.8098. Min Act: -0.1700
Data Index: 4136263 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4348. Min Range: -6.4348
Max Act: 5.8098. Min Act: -0.1698
Data Index: 7760769 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #19