Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3672 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.3074. Min Range: -3.3074
Max Act: 3.3074. Min Act: -0.1700
Data Index: 4587293 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3074. Min Range: -3.3074
Max Act: 3.1817. Min Act: -0.1700
Data Index: 1203667 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3074. Min Range: -3.3074
Max Act: 3.1187. Min Act: -0.1700
Data Index: 398368 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3074. Min Range: -3.3074
Max Act: 3.1187. Min Act: -0.1700
Data Index: 6192084 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3074. Min Range: -3.3074
Max Act: 3.1029. Min Act: -0.1700
Data Index: 4866606 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3074. Min Range: -3.3074
Max Act: 3.1029. Min Act: -0.1700
Data Index: 8739036 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3074. Min Range: -3.3074
Max Act: 3.0872. Min Act: -0.1700
Data Index: 2343603 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3074. Min Range: -3.3074
Max Act: 3.0872. Min Act: -0.1700
Data Index: 2549108 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3074. Min Range: -3.3074
Max Act: 3.0556. Min Act: -0.1700
Data Index: 2822720 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3074. Min Range: -3.3074
Max Act: 3.0714. Min Act: -0.1700
Data Index: 251332 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3074. Min Range: -3.3074
Max Act: 3.0714. Min Act: -0.1700
Data Index: 4206191 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3074. Min Range: -3.3074
Max Act: 3.0399. Min Act: -0.1700
Data Index: 5842304 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3074. Min Range: -3.3074
Max Act: 3.0556. Min Act: -0.1700
Data Index: 79098 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3074. Min Range: -3.3074
Max Act: 3.0241. Min Act: -0.1700
Data Index: 6016862 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3074. Min Range: -3.3074
Max Act: 3.0083. Min Act: -0.1700
Data Index: 8191034 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3074. Min Range: -3.3074
Max Act: 3.0083. Min Act: -0.1700
Data Index: 4034176 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3074. Min Range: -3.3074
Max Act: 3.0241. Min Act: -0.1700
Data Index: 5276031 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3074. Min Range: -3.3074
Max Act: 3.0241. Min Act: -0.1700
Data Index: 6546726 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3074. Min Range: -3.3074
Max Act: 3.0083. Min Act: -0.1700
Data Index: 2566673 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3074. Min Range: -3.3074
Max Act: 3.0241. Min Act: -0.1700
Data Index: 1083078 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #19