Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1342 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.3119. Min Range: -4.3119
Max Act: 4.3119. Min Act: -0.1700
Data Index: 6215550 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3119. Min Range: -4.3119
Max Act: 4.1869. Min Act: -0.1700
Data Index: 2479188 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3119. Min Range: -4.3119
Max Act: 4.1557. Min Act: -0.1700
Data Index: 5491966 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3119. Min Range: -4.3119
Max Act: 4.1869. Min Act: -0.1700
Data Index: 5325548 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3119. Min Range: -4.3119
Max Act: 4.1557. Min Act: -0.1700
Data Index: 637260 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3119. Min Range: -4.3119
Max Act: 4.1244. Min Act: -0.1700
Data Index: 6709626 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3119. Min Range: -4.3119
Max Act: 4.1244. Min Act: -0.1696
Data Index: 8425879 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3119. Min Range: -4.3119
Max Act: 4.0619. Min Act: -0.1700
Data Index: 5107663 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3119. Min Range: -4.3119
Max Act: 4.0619. Min Act: -0.1700
Data Index: 308782 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3119. Min Range: -4.3119
Max Act: 4.0619. Min Act: -0.1700
Data Index: 2589148 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3119. Min Range: -4.3119
Max Act: 4.0306. Min Act: -0.1700
Data Index: 6582916 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3119. Min Range: -4.3119
Max Act: 4.0306. Min Act: -0.1700
Data Index: 1920067 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3119. Min Range: -4.3119
Max Act: 4.0306. Min Act: -0.1700
Data Index: 1310635 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3119. Min Range: -4.3119
Max Act: 4.0306. Min Act: -0.1700
Data Index: 5046965 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3119. Min Range: -4.3119
Max Act: 4.0306. Min Act: -0.1700
Data Index: 5421202 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3119. Min Range: -4.3119
Max Act: 4.0306. Min Act: -0.1700
Data Index: 4171009 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3119. Min Range: -4.3119
Max Act: 4.0306. Min Act: -0.1700
Data Index: 2277434 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3119. Min Range: -4.3119
Max Act: 4.0306. Min Act: -0.1700
Data Index: 3869039 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3119. Min Range: -4.3119
Max Act: 3.9994. Min Act: -0.1700
Data Index: 3080328 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3119. Min Range: -4.3119
Max Act: 3.9994. Min Act: -0.1700
Data Index: 5823223 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19