Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1368 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8346. Min Range: -6.8346
Max Act: 6.8346. Min Act: -0.1700
Data Index: 7275161 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8346. Min Range: -6.8346
Max Act: 6.6471. Min Act: -0.1700
Data Index: 7207431 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8346. Min Range: -6.8346
Max Act: 6.5846. Min Act: -0.1700
Data Index: 4661824 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8346. Min Range: -6.8346
Max Act: 6.5846. Min Act: -0.1700
Data Index: 2587358 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8346. Min Range: -6.8346
Max Act: 6.4908. Min Act: -0.1700
Data Index: 2520783 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8346. Min Range: -6.8346
Max Act: 6.4283. Min Act: -0.1700
Data Index: 8194565 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8346. Min Range: -6.8346
Max Act: 6.4283. Min Act: -0.1700
Data Index: 1740614 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8346. Min Range: -6.8346
Max Act: 6.4283. Min Act: -0.1700
Data Index: 3576967 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8346. Min Range: -6.8346
Max Act: 6.3658. Min Act: -0.1700
Data Index: 2175113 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8346. Min Range: -6.8346
Max Act: 6.3658. Min Act: -0.1700
Data Index: 312083 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8346. Min Range: -6.8346
Max Act: 6.3346. Min Act: -0.1700
Data Index: 2639495 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8346. Min Range: -6.8346
Max Act: 6.3346. Min Act: -0.1700
Data Index: 8591584 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8346. Min Range: -6.8346
Max Act: 6.3658. Min Act: -0.1700
Data Index: 8823972 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8346. Min Range: -6.8346
Max Act: 6.3346. Min Act: -0.1700
Data Index: 122484 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8346. Min Range: -6.8346
Max Act: 6.3033. Min Act: -0.1700
Data Index: 3901107 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8346. Min Range: -6.8346
Max Act: 6.2721. Min Act: -0.1700
Data Index: 1657909 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8346. Min Range: -6.8346
Max Act: 6.2721. Min Act: -0.1700
Data Index: 4678619 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8346. Min Range: -6.8346
Max Act: 6.2721. Min Act: -0.1700
Data Index: 4900123 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8346. Min Range: -6.8346
Max Act: 6.2408. Min Act: -0.1700
Data Index: 3814135 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8346. Min Range: -6.8346
Max Act: 6.2721. Min Act: -0.1700
Data Index: 8225299 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #19