Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1942 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2456. Min Range: -5.2456
Max Act: 5.2144. Min Act: -0.1700
Data Index: 2614780 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2456. Min Range: -5.2456
Max Act: 5.2456. Min Act: -0.1700
Data Index: 7586055 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2456. Min Range: -5.2456
Max Act: 5.1519. Min Act: -0.1700
Data Index: 7482103 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2456. Min Range: -5.2456
Max Act: 5.0581. Min Act: -0.1700
Data Index: 312527 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2456. Min Range: -5.2456
Max Act: 5.0581. Min Act: -0.1700
Data Index: 5153394 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2456. Min Range: -5.2456
Max Act: 4.9644. Min Act: -0.1700
Data Index: 4086922 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2456. Min Range: -5.2456
Max Act: 4.9019. Min Act: -0.1700
Data Index: 1860039 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2456. Min Range: -5.2456
Max Act: 4.9019. Min Act: -0.1700
Data Index: 3532540 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2456. Min Range: -5.2456
Max Act: 4.9019. Min Act: -0.1700
Data Index: 7166803 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2456. Min Range: -5.2456
Max Act: 4.8706. Min Act: -0.1700
Data Index: 5875929 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2456. Min Range: -5.2456
Max Act: 4.8706. Min Act: -0.1700
Data Index: 5563219 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2456. Min Range: -5.2456
Max Act: 4.8706. Min Act: -0.1700
Data Index: 524730 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2456. Min Range: -5.2456
Max Act: 4.8706. Min Act: -0.1700
Data Index: 1029321 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2456. Min Range: -5.2456
Max Act: 4.8706. Min Act: -0.1700
Data Index: 4370335 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2456. Min Range: -5.2456
Max Act: 4.8394. Min Act: -0.1700
Data Index: 5227717 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2456. Min Range: -5.2456
Max Act: 4.8394. Min Act: -0.1700
Data Index: 1503233 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2456. Min Range: -5.2456
Max Act: 4.8081. Min Act: -0.1700
Data Index: 3279090 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2456. Min Range: -5.2456
Max Act: 4.8081. Min Act: -0.1700
Data Index: 5365451 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2456. Min Range: -5.2456
Max Act: 4.8081. Min Act: -0.1700
Data Index: 3538181 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2456. Min Range: -5.2456
Max Act: 4.8081. Min Act: -0.1700
Data Index: 5875927 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #19