Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3828 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.6699. Min Range: -2.6699
Max Act: 2.6699. Min Act: -0.1700
Data Index: 265045 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6699. Min Range: -2.6699
Max Act: 2.6218. Min Act: -0.1700
Data Index: 6746536 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6699. Min Range: -2.6699
Max Act: 2.6379. Min Act: -0.1700
Data Index: 4446201 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6699. Min Range: -2.6699
Max Act: 2.5735. Min Act: -0.1700
Data Index: 961490 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6699. Min Range: -2.6699
Max Act: 2.5735. Min Act: -0.1700
Data Index: 4186371 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6699. Min Range: -2.6699
Max Act: 2.5574. Min Act: -0.1700
Data Index: 7739859 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6699. Min Range: -2.6699
Max Act: 2.5735. Min Act: -0.1700
Data Index: 1656596 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6699. Min Range: -2.6699
Max Act: 2.5574. Min Act: -0.1700
Data Index: 7960255 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6699. Min Range: -2.6699
Max Act: 2.5735. Min Act: -0.1700
Data Index: 1082013 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6699. Min Range: -2.6699
Max Act: 2.5574. Min Act: -0.1700
Data Index: 2952041 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6699. Min Range: -2.6699
Max Act: 2.5251. Min Act: -0.1700
Data Index: 5481540 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6699. Min Range: -2.6699
Max Act: 2.5412. Min Act: -0.1700
Data Index: 6668889 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6699. Min Range: -2.6699
Max Act: 2.5412. Min Act: -0.1700
Data Index: 7926095 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6699. Min Range: -2.6699
Max Act: 2.5251. Min Act: -0.1700
Data Index: 5529739 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6699. Min Range: -2.6699
Max Act: 2.5251. Min Act: -0.1700
Data Index: 2199623 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6699. Min Range: -2.6699
Max Act: 2.5251. Min Act: -0.1700
Data Index: 7032348 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6699. Min Range: -2.6699
Max Act: 2.5251. Min Act: -0.1700
Data Index: 266400 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6699. Min Range: -2.6699
Max Act: 2.5089. Min Act: -0.1700
Data Index: 280610 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6699. Min Range: -2.6699
Max Act: 2.5089. Min Act: -0.1700
Data Index: 3661618 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6699. Min Range: -2.6699
Max Act: 2.5089. Min Act: -0.1700
Data Index: 7459358 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #19