Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 2978 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 5.9538. Min Range: -5.9538
Max Act: 5.9225. Min Act: -0.1700
Data Index: 7995539 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9538. Min Range: -5.9538
Max Act: 5.9538. Min Act: -0.1700
Data Index: 2491676 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9538. Min Range: -5.9538
Max Act: 5.8288. Min Act: -0.1700
Data Index: 4108619 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9538. Min Range: -5.9538
Max Act: 5.8288. Min Act: -0.1700
Data Index: 6615595 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9538. Min Range: -5.9538
Max Act: 5.7038. Min Act: -0.1700
Data Index: 5508436 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9538. Min Range: -5.9538
Max Act: 5.7350. Min Act: -0.1700
Data Index: 2365810 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9538. Min Range: -5.9538
Max Act: 5.7350. Min Act: -0.1700
Data Index: 4247369 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9538. Min Range: -5.9538
Max Act: 5.7350. Min Act: -0.1700
Data Index: 7503496 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9538. Min Range: -5.9538
Max Act: 5.6413. Min Act: -0.1700
Data Index: 6458233 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9538. Min Range: -5.9538
Max Act: 5.7038. Min Act: -0.1700
Data Index: 3672603 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9538. Min Range: -5.9538
Max Act: 5.6725. Min Act: -0.1700
Data Index: 3920292 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9538. Min Range: -5.9538
Max Act: 5.6100. Min Act: -0.1700
Data Index: 4684958 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9538. Min Range: -5.9538
Max Act: 5.6100. Min Act: -0.1700
Data Index: 6037395 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9538. Min Range: -5.9538
Max Act: 5.5788. Min Act: -0.1700
Data Index: 7012539 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9538. Min Range: -5.9538
Max Act: 5.6100. Min Act: -0.1700
Data Index: 3963579 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9538. Min Range: -5.9538
Max Act: 5.5788. Min Act: -0.1700
Data Index: 6336835 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9538. Min Range: -5.9538
Max Act: 5.5475. Min Act: -0.1700
Data Index: 1822730 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9538. Min Range: -5.9538
Max Act: 5.5163. Min Act: -0.1700
Data Index: 7803764 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9538. Min Range: -5.9538
Max Act: 5.5163. Min Act: -0.1700
Data Index: 1994328 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9538. Min Range: -5.9538
Max Act: 5.5163. Min Act: -0.1700
Data Index: 6334700 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #19