Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2963 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8477. Min Range: -5.8477
Max Act: 5.8477. Min Act: -0.1700
Data Index: 876066 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8477. Min Range: -5.8477
Max Act: 5.8164. Min Act: -0.1700
Data Index: 2687417 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8477. Min Range: -5.8477
Max Act: 5.7539. Min Act: -0.1700
Data Index: 3877180 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8477. Min Range: -5.8477
Max Act: 5.6602. Min Act: -0.1700
Data Index: 7867501 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8477. Min Range: -5.8477
Max Act: 5.5664. Min Act: -0.1700
Data Index: 4098318 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8477. Min Range: -5.8477
Max Act: 5.5039. Min Act: -0.1700
Data Index: 2883831 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8477. Min Range: -5.8477
Max Act: 5.5039. Min Act: -0.1700
Data Index: 2396029 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8477. Min Range: -5.8477
Max Act: 5.4727. Min Act: -0.1700
Data Index: 6404793 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8477. Min Range: -5.8477
Max Act: 5.4414. Min Act: -0.1700
Data Index: 6534965 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8477. Min Range: -5.8477
Max Act: 5.4414. Min Act: -0.1700
Data Index: 3470540 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8477. Min Range: -5.8477
Max Act: 5.4414. Min Act: -0.1700
Data Index: 1026344 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8477. Min Range: -5.8477
Max Act: 5.4414. Min Act: -0.1700
Data Index: 6806049 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8477. Min Range: -5.8477
Max Act: 5.4102. Min Act: -0.1700
Data Index: 3427890 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8477. Min Range: -5.8477
Max Act: 5.4102. Min Act: -0.1700
Data Index: 2060739 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8477. Min Range: -5.8477
Max Act: 5.4102. Min Act: -0.1700
Data Index: 1216773 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8477. Min Range: -5.8477
Max Act: 5.3789. Min Act: -0.1700
Data Index: 1885297 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8477. Min Range: -5.8477
Max Act: 5.3789. Min Act: -0.1700
Data Index: 7061558 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8477. Min Range: -5.8477
Max Act: 5.3789. Min Act: -0.1700
Data Index: 6542737 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8477. Min Range: -5.8477
Max Act: 5.3477. Min Act: -0.1700
Data Index: 4000638 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8477. Min Range: -5.8477
Max Act: 5.3789. Min Act: -0.1700
Data Index: 6097012 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #19