Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3891 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8054. Min Range: -3.8054
Max Act: 3.8054. Min Act: -0.1700
Data Index: 4511019 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8054. Min Range: -3.8054
Max Act: 3.7741. Min Act: -0.1700
Data Index: 6950111 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8054. Min Range: -3.8054
Max Act: 3.7741. Min Act: -0.1700
Data Index: 6797832 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8054. Min Range: -3.8054
Max Act: 3.7741. Min Act: -0.1700
Data Index: 4285596 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8054. Min Range: -3.8054
Max Act: 3.7741. Min Act: -0.1700
Data Index: 8611682 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8054. Min Range: -3.8054
Max Act: 3.7428. Min Act: -0.1700
Data Index: 7178019 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8054. Min Range: -3.8054
Max Act: 3.7428. Min Act: -0.1700
Data Index: 7203191 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8054. Min Range: -3.8054
Max Act: 3.7115. Min Act: -0.1700
Data Index: 7947505 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8054. Min Range: -3.8054
Max Act: 3.7115. Min Act: -0.1700
Data Index: 6181694 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8054. Min Range: -3.8054
Max Act: 3.7115. Min Act: -0.1700
Data Index: 5981323 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8054. Min Range: -3.8054
Max Act: 3.7115. Min Act: -0.1700
Data Index: 4470746 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8054. Min Range: -3.8054
Max Act: 3.7115. Min Act: -0.1700
Data Index: 4140711 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8054. Min Range: -3.8054
Max Act: 3.7115. Min Act: -0.1700
Data Index: 3132431 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8054. Min Range: -3.8054
Max Act: 3.7115. Min Act: -0.1700
Data Index: 5796303 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8054. Min Range: -3.8054
Max Act: 3.6803. Min Act: -0.1700
Data Index: 3803197 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8054. Min Range: -3.8054
Max Act: 3.6490. Min Act: -0.1700
Data Index: 2810365 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8054. Min Range: -3.8054
Max Act: 3.6490. Min Act: -0.1700
Data Index: 569795 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8054. Min Range: -3.8054
Max Act: 3.6490. Min Act: -0.1700
Data Index: 6331661 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8054. Min Range: -3.8054
Max Act: 3.6177. Min Act: -0.1700
Data Index: 163054 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8054. Min Range: -3.8054
Max Act: 3.6177. Min Act: -0.1700
Data Index: 3018777 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #19