Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4414 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 10.6051. Min Range: -10.6051
Max Act: 10.6051. Min Act: -0.1700
Data Index: 6379519 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.6051. Min Range: -10.6051
Max Act: 9.9176. Min Act: -0.1700
Data Index: 1540833 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.6051. Min Range: -10.6051
Max Act: 9.9176. Min Act: -0.1700
Data Index: 20230 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.6051. Min Range: -10.6051
Max Act: 9.7301. Min Act: -0.1700
Data Index: 4571534 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.6051. Min Range: -10.6051
Max Act: 9.7301. Min Act: -0.1700
Data Index: 2838587 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.6051. Min Range: -10.6051
Max Act: 9.7301. Min Act: -0.1700
Data Index: 7692350 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.6051. Min Range: -10.6051
Max Act: 9.5426. Min Act: -0.1700
Data Index: 2738360 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.6051. Min Range: -10.6051
Max Act: 9.5426. Min Act: -0.1700
Data Index: 2682413 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.6051. Min Range: -10.6051
Max Act: 9.5426. Min Act: -0.1700
Data Index: 1776450 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.6051. Min Range: -10.6051
Max Act: 9.4801. Min Act: -0.1700
Data Index: 2626160 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.6051. Min Range: -10.6051
Max Act: 9.4801. Min Act: -0.1700
Data Index: 5375979 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.6051. Min Range: -10.6051
Max Act: 9.4176. Min Act: -0.1700
Data Index: 8801324 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.6051. Min Range: -10.6051
Max Act: 9.4176. Min Act: -0.1700
Data Index: 8754782 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.6051. Min Range: -10.6051
Max Act: 9.4176. Min Act: -0.1700
Data Index: 6449065 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.6051. Min Range: -10.6051
Max Act: 9.4176. Min Act: -0.1700
Data Index: 3221431 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.6051. Min Range: -10.6051
Max Act: 9.4176. Min Act: -0.1700
Data Index: 7366889 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.6051. Min Range: -10.6051
Max Act: 9.4176. Min Act: -0.1700
Data Index: 270280 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.6051. Min Range: -10.6051
Max Act: 9.4176. Min Act: -0.1700
Data Index: 4316220 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.6051. Min Range: -10.6051
Max Act: 9.4176. Min Act: -0.1700
Data Index: 211881 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.6051. Min Range: -10.6051
Max Act: 9.4801. Min Act: -0.1700
Data Index: 7024989 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #19