Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6284 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.6380. Min Range: -2.6380
Max Act: 2.6380. Min Act: -0.1700
Data Index: 1461965 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6380. Min Range: -2.6380
Max Act: 2.5575. Min Act: -0.1700
Data Index: 6221826 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6380. Min Range: -2.6380
Max Act: 2.3626. Min Act: -0.1700
Data Index: 7462518 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6380. Min Range: -2.6380
Max Act: 2.3626. Min Act: -0.1700
Data Index: 1461966 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6380. Min Range: -2.6380
Max Act: 2.3462. Min Act: -0.1700
Data Index: 3090404 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6380. Min Range: -2.6380
Max Act: 2.3298. Min Act: -0.1700
Data Index: 4692256 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6380. Min Range: -2.6380
Max Act: 2.3298. Min Act: -0.1700
Data Index: 1712993 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6380. Min Range: -2.6380
Max Act: 2.3134. Min Act: -0.1700
Data Index: 1406886 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6380. Min Range: -2.6380
Max Act: 2.3134. Min Act: -0.1700
Data Index: 8638033 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6380. Min Range: -2.6380
Max Act: 2.2969. Min Act: -0.1700
Data Index: 4167282 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6380. Min Range: -2.6380
Max Act: 2.2804. Min Act: -0.1700
Data Index: 2436368 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6380. Min Range: -2.6380
Max Act: 2.2969. Min Act: -0.1700
Data Index: 6859085 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6380. Min Range: -2.6380
Max Act: 2.2969. Min Act: -0.1700
Data Index: 4108825 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6380. Min Range: -2.6380
Max Act: 2.2804. Min Act: -0.1700
Data Index: 8212958 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6380. Min Range: -2.6380
Max Act: 2.2804. Min Act: -0.1700
Data Index: 2090876 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6380. Min Range: -2.6380
Max Act: 2.2640. Min Act: -0.1700
Data Index: 7407072 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6380. Min Range: -2.6380
Max Act: 2.2804. Min Act: -0.1700
Data Index: 2213856 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6380. Min Range: -2.6380
Max Act: 2.2640. Min Act: -0.1700
Data Index: 5466795 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6380. Min Range: -2.6380
Max Act: 2.2640. Min Act: -0.1700
Data Index: 2222524 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6380. Min Range: -2.6380
Max Act: 2.2640. Min Act: -0.1700
Data Index: 3947633 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #19