Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 913 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2567. Min Range: -6.2567
Max Act: 6.2567. Min Act: -0.1700
Data Index: 8566988 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2567. Min Range: -6.2567
Max Act: 6.1942. Min Act: -0.1700
Data Index: 1986591 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2567. Min Range: -6.2567
Max Act: 5.9754. Min Act: -0.1700
Data Index: 4047743 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2567. Min Range: -6.2567
Max Act: 5.9442. Min Act: -0.1700
Data Index: 6124331 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2567. Min Range: -6.2567
Max Act: 5.9754. Min Act: -0.1700
Data Index: 7909531 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2567. Min Range: -6.2567
Max Act: 5.8817. Min Act: -0.1700
Data Index: 7343761 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2567. Min Range: -6.2567
Max Act: 5.8504. Min Act: -0.1700
Data Index: 3270158 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2567. Min Range: -6.2567
Max Act: 5.8504. Min Act: -0.1700
Data Index: 3786048 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2567. Min Range: -6.2567
Max Act: 5.8192. Min Act: -0.1700
Data Index: 2105079 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2567. Min Range: -6.2567
Max Act: 5.8192. Min Act: -0.1700
Data Index: 4387763 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2567. Min Range: -6.2567
Max Act: 5.7879. Min Act: -0.1700
Data Index: 8332051 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2567. Min Range: -6.2567
Max Act: 5.7254. Min Act: -0.1700
Data Index: 6402835 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2567. Min Range: -6.2567
Max Act: 5.7567. Min Act: -0.1700
Data Index: 272830 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2567. Min Range: -6.2567
Max Act: 5.7254. Min Act: -0.1699
Data Index: 5617109 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2567. Min Range: -6.2567
Max Act: 5.7254. Min Act: -0.1700
Data Index: 8508656 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2567. Min Range: -6.2567
Max Act: 5.7254. Min Act: -0.1700
Data Index: 5311640 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2567. Min Range: -6.2567
Max Act: 5.7254. Min Act: -0.1700
Data Index: 7993560 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2567. Min Range: -6.2567
Max Act: 5.6942. Min Act: -0.1700
Data Index: 1168549 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2567. Min Range: -6.2567
Max Act: 5.6942. Min Act: -0.1700
Data Index: 5011971 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2567. Min Range: -6.2567
Max Act: 5.6942. Min Act: -0.1700
Data Index: 2008356 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #19