Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1504 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.8406. Min Range: -5.8406
Max Act: 5.8406. Min Act: -0.1700
Data Index: 8090928 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8406. Min Range: -5.8406
Max Act: 5.7781. Min Act: -0.1700
Data Index: 7153944 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8406. Min Range: -5.8406
Max Act: 5.7781. Min Act: -0.1700
Data Index: 8370610 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8406. Min Range: -5.8406
Max Act: 5.6531. Min Act: -0.1700
Data Index: 8614693 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8406. Min Range: -5.8406
Max Act: 5.6844. Min Act: -0.1700
Data Index: 8679833 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8406. Min Range: -5.8406
Max Act: 5.6531. Min Act: -0.1700
Data Index: 8689348 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8406. Min Range: -5.8406
Max Act: 5.5594. Min Act: -0.1700
Data Index: 250964 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8406. Min Range: -5.8406
Max Act: 5.5281. Min Act: -0.1700
Data Index: 3830447 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8406. Min Range: -5.8406
Max Act: 5.5281. Min Act: -0.1700
Data Index: 5378701 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8406. Min Range: -5.8406
Max Act: 5.5281. Min Act: -0.1700
Data Index: 6675351 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8406. Min Range: -5.8406
Max Act: 5.5281. Min Act: -0.1700
Data Index: 8466338 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8406. Min Range: -5.8406
Max Act: 5.5281. Min Act: -0.1700
Data Index: 3967028 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8406. Min Range: -5.8406
Max Act: 5.5281. Min Act: -0.1700
Data Index: 1807128 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8406. Min Range: -5.8406
Max Act: 5.4969. Min Act: -0.1700
Data Index: 2088569 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8406. Min Range: -5.8406
Max Act: 5.4656. Min Act: -0.1700
Data Index: 4495540 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8406. Min Range: -5.8406
Max Act: 5.4656. Min Act: -0.1700
Data Index: 791206 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8406. Min Range: -5.8406
Max Act: 5.5281. Min Act: -0.1700
Data Index: 8532645 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8406. Min Range: -5.8406
Max Act: 5.4969. Min Act: -0.1700
Data Index: 4281478 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8406. Min Range: -5.8406
Max Act: 5.4656. Min Act: -0.1700
Data Index: 3865803 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8406. Min Range: -5.8406
Max Act: 5.4656. Min Act: -0.1700
Data Index: 1246464 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #19