Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 107 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.9258. Min Range: -4.9258
Max Act: 4.9258. Min Act: -0.1700
Data Index: 4197868 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9258. Min Range: -4.9258
Max Act: 4.8945. Min Act: -0.1700
Data Index: 1920186 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9258. Min Range: -4.9258
Max Act: 4.8633. Min Act: -0.1700
Data Index: 7815003 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9258. Min Range: -4.9258
Max Act: 4.8633. Min Act: -0.1700
Data Index: 6283597 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9258. Min Range: -4.9258
Max Act: 4.8320. Min Act: -0.1700
Data Index: 7405185 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9258. Min Range: -4.9258
Max Act: 4.8320. Min Act: -0.1700
Data Index: 8192480 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9258. Min Range: -4.9258
Max Act: 4.8008. Min Act: -0.1700
Data Index: 3995680 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9258. Min Range: -4.9258
Max Act: 4.8008. Min Act: -0.1700
Data Index: 7235671 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9258. Min Range: -4.9258
Max Act: 4.8320. Min Act: -0.1700
Data Index: 4285823 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9258. Min Range: -4.9258
Max Act: 4.8008. Min Act: -0.1700
Data Index: 3760412 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9258. Min Range: -4.9258
Max Act: 4.8008. Min Act: -0.1700
Data Index: 8467035 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9258. Min Range: -4.9258
Max Act: 4.8008. Min Act: -0.1700
Data Index: 3541678 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9258. Min Range: -4.9258
Max Act: 4.8320. Min Act: -0.1700
Data Index: 2770715 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9258. Min Range: -4.9258
Max Act: 4.8008. Min Act: -0.1700
Data Index: 4830820 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9258. Min Range: -4.9258
Max Act: 4.7695. Min Act: -0.1700
Data Index: 5608516 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9258. Min Range: -4.9258
Max Act: 4.7695. Min Act: -0.1700
Data Index: 5777447 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9258. Min Range: -4.9258
Max Act: 4.7695. Min Act: -0.1700
Data Index: 554913 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9258. Min Range: -4.9258
Max Act: 4.7695. Min Act: -0.1700
Data Index: 7340165 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9258. Min Range: -4.9258
Max Act: 4.7695. Min Act: -0.1700
Data Index: 1756541 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9258. Min Range: -4.9258
Max Act: 4.7695. Min Act: -0.1700
Data Index: 4459695 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19