Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2006 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.0784. Min Range: -4.0784
Max Act: 4.0784. Min Act: -0.1700
Data Index: 5380906 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0784. Min Range: -4.0784
Max Act: 4.0784. Min Act: -0.1700
Data Index: 6713468 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0784. Min Range: -4.0784
Max Act: 4.0471. Min Act: -0.1700
Data Index: 3555226 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0784. Min Range: -4.0784
Max Act: 4.0471. Min Act: -0.1700
Data Index: 8830625 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0784. Min Range: -4.0784
Max Act: 4.0471. Min Act: -0.1700
Data Index: 4570148 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0784. Min Range: -4.0784
Max Act: 4.0158. Min Act: -0.1700
Data Index: 132936 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0784. Min Range: -4.0784
Max Act: 4.0158. Min Act: -0.1700
Data Index: 2433140 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0784. Min Range: -4.0784
Max Act: 4.0158. Min Act: -0.1700
Data Index: 5312893 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0784. Min Range: -4.0784
Max Act: 4.0158. Min Act: -0.1700
Data Index: 7838227 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0784. Min Range: -4.0784
Max Act: 4.0158. Min Act: -0.1700
Data Index: 5180007 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0784. Min Range: -4.0784
Max Act: 4.0158. Min Act: -0.1700
Data Index: 7273353 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0784. Min Range: -4.0784
Max Act: 4.0158. Min Act: -0.1700
Data Index: 5558304 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0784. Min Range: -4.0784
Max Act: 3.9846. Min Act: -0.1700
Data Index: 6490809 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0784. Min Range: -4.0784
Max Act: 4.0158. Min Act: -0.1700
Data Index: 4400241 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0784. Min Range: -4.0784
Max Act: 4.0158. Min Act: -0.1700
Data Index: 376684 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0784. Min Range: -4.0784
Max Act: 4.0158. Min Act: -0.1700
Data Index: 5890910 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0784. Min Range: -4.0784
Max Act: 4.0158. Min Act: -0.1700
Data Index: 1236046 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0784. Min Range: -4.0784
Max Act: 4.0158. Min Act: -0.1700
Data Index: 1000184 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0784. Min Range: -4.0784
Max Act: 3.9846. Min Act: -0.1700
Data Index: 638638 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0784. Min Range: -4.0784
Max Act: 3.9846. Min Act: -0.1700
Data Index: 2266118 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19