Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2607 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5211. Min Range: -5.5211
Max Act: 5.5211. Min Act: -0.1700
Data Index: 2701427 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5211. Min Range: -5.5211
Max Act: 5.2398. Min Act: -0.1700
Data Index: 552742 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5211. Min Range: -5.5211
Max Act: 5.1773. Min Act: -0.1700
Data Index: 3264144 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5211. Min Range: -5.5211
Max Act: 5.1461. Min Act: -0.1700
Data Index: 1291611 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5211. Min Range: -5.5211
Max Act: 5.1461. Min Act: -0.1700
Data Index: 60387 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5211. Min Range: -5.5211
Max Act: 5.0523. Min Act: -0.1700
Data Index: 3876363 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5211. Min Range: -5.5211
Max Act: 5.0211. Min Act: -0.1700
Data Index: 7672972 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5211. Min Range: -5.5211
Max Act: 4.9898. Min Act: -0.1700
Data Index: 2416863 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5211. Min Range: -5.5211
Max Act: 4.9898. Min Act: -0.1700
Data Index: 3679795 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5211. Min Range: -5.5211
Max Act: 4.9273. Min Act: -0.1700
Data Index: 5054494 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5211. Min Range: -5.5211
Max Act: 4.9273. Min Act: -0.1700
Data Index: 594290 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5211. Min Range: -5.5211
Max Act: 4.9586. Min Act: -0.1700
Data Index: 4748725 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5211. Min Range: -5.5211
Max Act: 4.9586. Min Act: -0.1700
Data Index: 7875920 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5211. Min Range: -5.5211
Max Act: 4.9898. Min Act: -0.1700
Data Index: 6237977 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5211. Min Range: -5.5211
Max Act: 4.9586. Min Act: -0.1700
Data Index: 4145223 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5211. Min Range: -5.5211
Max Act: 4.9273. Min Act: -0.1700
Data Index: 30310 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5211. Min Range: -5.5211
Max Act: 4.9273. Min Act: -0.1700
Data Index: 3616828 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5211. Min Range: -5.5211
Max Act: 4.9273. Min Act: -0.1700
Data Index: 1364286 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5211. Min Range: -5.5211
Max Act: 4.9273. Min Act: -0.1700
Data Index: 4985278 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5211. Min Range: -5.5211
Max Act: 4.9273. Min Act: -0.1700
Data Index: 4961900 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #19