Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1733 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0323. Min Range: -5.0323
Max Act: 5.0323. Min Act: -0.1700
Data Index: 894742 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0323. Min Range: -5.0323
Max Act: 5.0323. Min Act: -0.1700
Data Index: 2070491 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0323. Min Range: -5.0323
Max Act: 5.0011. Min Act: -0.1700
Data Index: 1173580 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0323. Min Range: -5.0323
Max Act: 5.0011. Min Act: -0.1700
Data Index: 7928905 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0323. Min Range: -5.0323
Max Act: 5.0011. Min Act: -0.1700
Data Index: 7062669 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0323. Min Range: -5.0323
Max Act: 5.0011. Min Act: -0.1700
Data Index: 1093181 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0323. Min Range: -5.0323
Max Act: 5.0011. Min Act: -0.1700
Data Index: 621600 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0323. Min Range: -5.0323
Max Act: 5.0011. Min Act: -0.1700
Data Index: 1633759 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0323. Min Range: -5.0323
Max Act: 5.0011. Min Act: -0.1700
Data Index: 4041358 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0323. Min Range: -5.0323
Max Act: 5.0011. Min Act: -0.1700
Data Index: 1093189 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0323. Min Range: -5.0323
Max Act: 5.0011. Min Act: -0.1700
Data Index: 4231326 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0323. Min Range: -5.0323
Max Act: 4.9698. Min Act: -0.1700
Data Index: 5037384 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0323. Min Range: -5.0323
Max Act: 4.9698. Min Act: -0.1700
Data Index: 4833800 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0323. Min Range: -5.0323
Max Act: 4.9698. Min Act: -0.1700
Data Index: 4718963 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0323. Min Range: -5.0323
Max Act: 4.9386. Min Act: -0.1700
Data Index: 4661288 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0323. Min Range: -5.0323
Max Act: 4.9698. Min Act: -0.1700
Data Index: 1093184 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0323. Min Range: -5.0323
Max Act: 4.9386. Min Act: -0.1700
Data Index: 1647332 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0323. Min Range: -5.0323
Max Act: 4.9698. Min Act: -0.1700
Data Index: 3189205 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0323. Min Range: -5.0323
Max Act: 4.9698. Min Act: -0.1700
Data Index: 1093180 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0323. Min Range: -5.0323
Max Act: 5.0011. Min Act: -0.1700
Data Index: 2823853 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #19