Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 658 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8185. Min Range: -3.8185
Max Act: 3.8185. Min Act: -0.1700
Data Index: 8284410 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8185. Min Range: -3.8185
Max Act: 3.7872. Min Act: -0.1700
Data Index: 3138990 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8185. Min Range: -3.8185
Max Act: 3.7559. Min Act: -0.1700
Data Index: 2911472 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8185. Min Range: -3.8185
Max Act: 3.7559. Min Act: -0.1700
Data Index: 4044767 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8185. Min Range: -3.8185
Max Act: 3.7559. Min Act: -0.1700
Data Index: 944245 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8185. Min Range: -3.8185
Max Act: 3.7559. Min Act: -0.1700
Data Index: 183803 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8185. Min Range: -3.8185
Max Act: 3.7246. Min Act: -0.1700
Data Index: 1975754 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8185. Min Range: -3.8185
Max Act: 3.7246. Min Act: -0.1700
Data Index: 1115512 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8185. Min Range: -3.8185
Max Act: 3.7246. Min Act: -0.1700
Data Index: 1329494 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8185. Min Range: -3.8185
Max Act: 3.7246. Min Act: -0.1700
Data Index: 5636227 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8185. Min Range: -3.8185
Max Act: 3.7246. Min Act: -0.1700
Data Index: 8230976 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8185. Min Range: -3.8185
Max Act: 3.7246. Min Act: -0.1700
Data Index: 1236555 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8185. Min Range: -3.8185
Max Act: 3.7246. Min Act: -0.1700
Data Index: 7852964 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8185. Min Range: -3.8185
Max Act: 3.7246. Min Act: -0.1700
Data Index: 7187466 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8185. Min Range: -3.8185
Max Act: 3.7246. Min Act: -0.1700
Data Index: 6736129 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8185. Min Range: -3.8185
Max Act: 3.6933. Min Act: -0.1700
Data Index: 7895983 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8185. Min Range: -3.8185
Max Act: 3.6933. Min Act: -0.1700
Data Index: 2967723 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8185. Min Range: -3.8185
Max Act: 3.6933. Min Act: -0.1700
Data Index: 4957586 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8185. Min Range: -3.8185
Max Act: 3.6933. Min Act: -0.1700
Data Index: 4940019 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8185. Min Range: -3.8185
Max Act: 3.6933. Min Act: -0.1700
Data Index: 6344563 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19