Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2785 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0495. Min Range: -5.0495
Max Act: 5.0495. Min Act: -0.1700
Data Index: 4315268 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0495. Min Range: -5.0495
Max Act: 4.8620. Min Act: -0.1700
Data Index: 5737309 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0495. Min Range: -5.0495
Max Act: 4.7682. Min Act: -0.1700
Data Index: 4406833 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0495. Min Range: -5.0495
Max Act: 4.7682. Min Act: -0.1700
Data Index: 1915731 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0495. Min Range: -5.0495
Max Act: 4.7370. Min Act: -0.1700
Data Index: 3078464 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0495. Min Range: -5.0495
Max Act: 4.6745. Min Act: -0.1700
Data Index: 3183244 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0495. Min Range: -5.0495
Max Act: 4.7057. Min Act: -0.1700
Data Index: 6565327 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0495. Min Range: -5.0495
Max Act: 4.6745. Min Act: -0.1700
Data Index: 3511562 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0495. Min Range: -5.0495
Max Act: 4.7057. Min Act: -0.1700
Data Index: 1501067 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0495. Min Range: -5.0495
Max Act: 4.6745. Min Act: -0.1700
Data Index: 7414331 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0495. Min Range: -5.0495
Max Act: 4.7057. Min Act: -0.1700
Data Index: 5384730 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0495. Min Range: -5.0495
Max Act: 4.6745. Min Act: -0.1700
Data Index: 8553118 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0495. Min Range: -5.0495
Max Act: 4.6120. Min Act: -0.1700
Data Index: 2243072 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0495. Min Range: -5.0495
Max Act: 4.6432. Min Act: -0.1700
Data Index: 758692 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0495. Min Range: -5.0495
Max Act: 4.6432. Min Act: -0.1700
Data Index: 8132010 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0495. Min Range: -5.0495
Max Act: 4.5807. Min Act: -0.1700
Data Index: 3557980 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0495. Min Range: -5.0495
Max Act: 4.6432. Min Act: -0.1700
Data Index: 4201693 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0495. Min Range: -5.0495
Max Act: 4.6120. Min Act: -0.1700
Data Index: 8668561 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0495. Min Range: -5.0495
Max Act: 4.6120. Min Act: -0.1700
Data Index: 8650299 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0495. Min Range: -5.0495
Max Act: 4.6120. Min Act: -0.1700
Data Index: 4217720 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19