Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3290 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8784. Min Range: -5.8784
Max Act: 5.8784. Min Act: -0.1700
Data Index: 1103950 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8784. Min Range: -5.8784
Max Act: 5.8472. Min Act: -0.1700
Data Index: 8477796 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8784. Min Range: -5.8784
Max Act: 5.8159. Min Act: -0.1700
Data Index: 6634448 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8784. Min Range: -5.8784
Max Act: 5.8159. Min Act: -0.1700
Data Index: 1855294 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8784. Min Range: -5.8784
Max Act: 5.8159. Min Act: -0.1700
Data Index: 3639927 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8784. Min Range: -5.8784
Max Act: 5.8159. Min Act: -0.1700
Data Index: 8182438 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8784. Min Range: -5.8784
Max Act: 5.8159. Min Act: -0.1700
Data Index: 5500873 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8784. Min Range: -5.8784
Max Act: 5.7847. Min Act: -0.1700
Data Index: 1251446 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8784. Min Range: -5.8784
Max Act: 5.7847. Min Act: -0.1700
Data Index: 2429227 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8784. Min Range: -5.8784
Max Act: 5.7847. Min Act: -0.1700
Data Index: 3139898 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8784. Min Range: -5.8784
Max Act: 5.7847. Min Act: -0.1700
Data Index: 434640 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8784. Min Range: -5.8784
Max Act: 5.7534. Min Act: -0.1700
Data Index: 8035763 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8784. Min Range: -5.8784
Max Act: 5.7534. Min Act: -0.1700
Data Index: 3782744 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8784. Min Range: -5.8784
Max Act: 5.7534. Min Act: -0.1700
Data Index: 2763002 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8784. Min Range: -5.8784
Max Act: 5.7534. Min Act: -0.1700
Data Index: 2477741 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8784. Min Range: -5.8784
Max Act: 5.7534. Min Act: -0.1700
Data Index: 7788792 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8784. Min Range: -5.8784
Max Act: 5.7534. Min Act: -0.1700
Data Index: 4949282 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8784. Min Range: -5.8784
Max Act: 5.7534. Min Act: -0.1700
Data Index: 1224805 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8784. Min Range: -5.8784
Max Act: 5.7534. Min Act: -0.1700
Data Index: 6045553 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8784. Min Range: -5.8784
Max Act: 5.7222. Min Act: -0.1700
Data Index: 1028320 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19