Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3451 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3786. Min Range: -6.3786
Max Act: 6.3473. Min Act: -0.1700
Data Index: 8429078 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3786. Min Range: -6.3786
Max Act: 6.3786. Min Act: -0.1700
Data Index: 7928489 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3786. Min Range: -6.3786
Max Act: 6.2223. Min Act: -0.1700
Data Index: 5327940 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3786. Min Range: -6.3786
Max Act: 6.1598. Min Act: -0.1700
Data Index: 8553689 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3786. Min Range: -6.3786
Max Act: 6.0348. Min Act: -0.1700
Data Index: 2376426 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3786. Min Range: -6.3786
Max Act: 6.0348. Min Act: -0.1700
Data Index: 5922045 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3786. Min Range: -6.3786
Max Act: 5.9411. Min Act: -0.1700
Data Index: 6820884 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3786. Min Range: -6.3786
Max Act: 5.8786. Min Act: -0.1700
Data Index: 763853 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3786. Min Range: -6.3786
Max Act: 5.8473. Min Act: -0.1700
Data Index: 1180325 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3786. Min Range: -6.3786
Max Act: 5.8473. Min Act: -0.1700
Data Index: 2419331 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3786. Min Range: -6.3786
Max Act: 5.8161. Min Act: -0.1700
Data Index: 3777903 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3786. Min Range: -6.3786
Max Act: 5.7848. Min Act: -0.1700
Data Index: 1995330 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3786. Min Range: -6.3786
Max Act: 5.8161. Min Act: -0.1700
Data Index: 5253721 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3786. Min Range: -6.3786
Max Act: 5.7848. Min Act: -0.1700
Data Index: 7896385 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3786. Min Range: -6.3786
Max Act: 5.8473. Min Act: -0.1700
Data Index: 414823 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3786. Min Range: -6.3786
Max Act: 5.8161. Min Act: -0.1700
Data Index: 2942210 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3786. Min Range: -6.3786
Max Act: 5.8161. Min Act: -0.1700
Data Index: 1082619 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3786. Min Range: -6.3786
Max Act: 5.7536. Min Act: -0.1700
Data Index: 4537296 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3786. Min Range: -6.3786
Max Act: 5.8161. Min Act: -0.1700
Data Index: 6551618 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3786. Min Range: -6.3786
Max Act: 5.7848. Min Act: -0.1700
Data Index: 3566398 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #19