Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3735 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4519. Min Range: -3.4519
Max Act: 3.4519. Min Act: -0.1700
Data Index: 2053049 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4519. Min Range: -3.4519
Max Act: 3.4362. Min Act: -0.1700
Data Index: 878992 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4519. Min Range: -3.4519
Max Act: 3.4362. Min Act: -0.1700
Data Index: 1429193 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4519. Min Range: -3.4519
Max Act: 3.4362. Min Act: -0.1700
Data Index: 1819042 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4519. Min Range: -3.4519
Max Act: 3.4205. Min Act: -0.1700
Data Index: 3932035 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4519. Min Range: -3.4519
Max Act: 3.4205. Min Act: -0.1700
Data Index: 5385068 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4519. Min Range: -3.4519
Max Act: 3.4205. Min Act: -0.1700
Data Index: 7580336 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4519. Min Range: -3.4519
Max Act: 3.4205. Min Act: -0.1700
Data Index: 42833 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4519. Min Range: -3.4519
Max Act: 3.4205. Min Act: -0.1700
Data Index: 3455065 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4519. Min Range: -3.4519
Max Act: 3.4205. Min Act: -0.1700
Data Index: 2271540 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4519. Min Range: -3.4519
Max Act: 3.4049. Min Act: -0.1700
Data Index: 6633562 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4519. Min Range: -3.4519
Max Act: 3.4049. Min Act: -0.1700
Data Index: 1251771 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4519. Min Range: -3.4519
Max Act: 3.4049. Min Act: -0.1700
Data Index: 798922 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4519. Min Range: -3.4519
Max Act: 3.4049. Min Act: -0.1700
Data Index: 6518611 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4519. Min Range: -3.4519
Max Act: 3.4049. Min Act: -0.1700
Data Index: 8372594 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4519. Min Range: -3.4519
Max Act: 3.4049. Min Act: -0.1700
Data Index: 7638114 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4519. Min Range: -3.4519
Max Act: 3.4049. Min Act: -0.1700
Data Index: 2654683 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4519. Min Range: -3.4519
Max Act: 3.4049. Min Act: -0.1700
Data Index: 961787 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4519. Min Range: -3.4519
Max Act: 3.3892. Min Act: -0.1700
Data Index: 6329712 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4519. Min Range: -3.4519
Max Act: 3.3892. Min Act: -0.1700
Data Index: 3367377 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19