Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 362 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.8170. Min Range: -1.8170
Max Act: 1.8170. Min Act: -0.1700
Data Index: 7196807 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8170. Min Range: -1.8170
Max Act: 1.7826. Min Act: -0.1700
Data Index: 12302 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8170. Min Range: -1.8170
Max Act: 1.7912. Min Act: -0.1699
Data Index: 4518768 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8170. Min Range: -1.8170
Max Act: 1.7395. Min Act: -0.1700
Data Index: 6215151 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8170. Min Range: -1.8170
Max Act: 1.7568. Min Act: -0.1700
Data Index: 5437025 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8170. Min Range: -1.8170
Max Act: 1.7395. Min Act: -0.1700
Data Index: 1585661 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8170. Min Range: -1.8170
Max Act: 1.7395. Min Act: -0.1700
Data Index: 6270123 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8170. Min Range: -1.8170
Max Act: 1.7395. Min Act: -0.1700
Data Index: 4567630 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8170. Min Range: -1.8170
Max Act: 1.7308. Min Act: -0.1700
Data Index: 1817617 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8170. Min Range: -1.8170
Max Act: 1.7308. Min Act: -0.1700
Data Index: 756140 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8170. Min Range: -1.8170
Max Act: 1.7308. Min Act: -0.1700
Data Index: 5492646 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8170. Min Range: -1.8170
Max Act: 1.7308. Min Act: -0.1700
Data Index: 8168382 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8170. Min Range: -1.8170
Max Act: 1.7308. Min Act: -0.1697
Data Index: 3098943 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8170. Min Range: -1.8170
Max Act: 1.7222. Min Act: -0.1700
Data Index: 1659570 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8170. Min Range: -1.8170
Max Act: 1.7222. Min Act: -0.1700
Data Index: 970208 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8170. Min Range: -1.8170
Max Act: 1.7222. Min Act: -0.1697
Data Index: 8256917 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8170. Min Range: -1.8170
Max Act: 1.7135. Min Act: -0.1700
Data Index: 2842394 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8170. Min Range: -1.8170
Max Act: 1.7222. Min Act: -0.1700
Data Index: 8197804 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8170. Min Range: -1.8170
Max Act: 1.7049. Min Act: -0.1700
Data Index: 237449 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8170. Min Range: -1.8170
Max Act: 1.7135. Min Act: -0.1700
Data Index: 7993740 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #19