Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4836 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.2472. Min Range: -4.2472
Max Act: 4.2472. Min Act: -0.1700
Data Index: 5190707 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2472. Min Range: -4.2472
Max Act: 4.1847. Min Act: -0.1700
Data Index: 1744912 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2472. Min Range: -4.2472
Max Act: 4.1847. Min Act: -0.1700
Data Index: 4125623 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2472. Min Range: -4.2472
Max Act: 4.1535. Min Act: -0.1700
Data Index: 5196006 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2472. Min Range: -4.2472
Max Act: 4.1222. Min Act: -0.1700
Data Index: 8530864 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2472. Min Range: -4.2472
Max Act: 4.0910. Min Act: -0.1700
Data Index: 8372896 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2472. Min Range: -4.2472
Max Act: 4.0910. Min Act: -0.1699
Data Index: 6626507 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2472. Min Range: -4.2472
Max Act: 4.0597. Min Act: -0.1700
Data Index: 6072814 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2472. Min Range: -4.2472
Max Act: 4.0910. Min Act: -0.1700
Data Index: 212832 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2472. Min Range: -4.2472
Max Act: 4.0910. Min Act: -0.1700
Data Index: 5495305 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2472. Min Range: -4.2472
Max Act: 4.0910. Min Act: -0.1700
Data Index: 3284252 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2472. Min Range: -4.2472
Max Act: 4.0910. Min Act: -0.1700
Data Index: 4708492 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2472. Min Range: -4.2472
Max Act: 4.0910. Min Act: -0.1700
Data Index: 7111469 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2472. Min Range: -4.2472
Max Act: 4.0597. Min Act: -0.1700
Data Index: 4808204 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2472. Min Range: -4.2472
Max Act: 4.0597. Min Act: -0.1700
Data Index: 4731843 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2472. Min Range: -4.2472
Max Act: 4.0910. Min Act: -0.1700
Data Index: 5351058 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2472. Min Range: -4.2472
Max Act: 4.0284. Min Act: -0.1700
Data Index: 5592185 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2472. Min Range: -4.2472
Max Act: 4.0284. Min Act: -0.1700
Data Index: 4494021 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2472. Min Range: -4.2472
Max Act: 4.0597. Min Act: -0.1700
Data Index: 690968 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2472. Min Range: -4.2472
Max Act: 4.0597. Min Act: -0.1700
Data Index: 2353116 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #19