Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5462 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7929. Min Range: -5.7929
Max Act: 5.7929. Min Act: -0.1700
Data Index: 8398880 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7929. Min Range: -5.7929
Max Act: 5.6992. Min Act: -0.1700
Data Index: 7516115 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7929. Min Range: -5.7929
Max Act: 5.5117. Min Act: -0.1700
Data Index: 792798 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7929. Min Range: -5.7929
Max Act: 5.5117. Min Act: -0.1700
Data Index: 4043968 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7929. Min Range: -5.7929
Max Act: 5.4179. Min Act: -0.1700
Data Index: 4741618 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7929. Min Range: -5.7929
Max Act: 5.3867. Min Act: -0.1700
Data Index: 6344991 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7929. Min Range: -5.7929
Max Act: 5.3554. Min Act: -0.1700
Data Index: 4208949 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7929. Min Range: -5.7929
Max Act: 5.3242. Min Act: -0.1700
Data Index: 2831977 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7929. Min Range: -5.7929
Max Act: 5.3242. Min Act: -0.1700
Data Index: 6247092 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7929. Min Range: -5.7929
Max Act: 5.3242. Min Act: -0.1700
Data Index: 3239933 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7929. Min Range: -5.7929
Max Act: 5.3242. Min Act: -0.1700
Data Index: 1029428 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7929. Min Range: -5.7929
Max Act: 5.2929. Min Act: -0.1700
Data Index: 113973 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7929. Min Range: -5.7929
Max Act: 5.2617. Min Act: -0.1700
Data Index: 6727376 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7929. Min Range: -5.7929
Max Act: 5.2617. Min Act: -0.1700
Data Index: 3037990 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7929. Min Range: -5.7929
Max Act: 5.2617. Min Act: -0.1700
Data Index: 6482604 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7929. Min Range: -5.7929
Max Act: 5.2304. Min Act: -0.1700
Data Index: 8777827 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7929. Min Range: -5.7929
Max Act: 5.2617. Min Act: -0.1700
Data Index: 7387812 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7929. Min Range: -5.7929
Max Act: 5.2304. Min Act: -0.1700
Data Index: 529030 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7929. Min Range: -5.7929
Max Act: 5.2304. Min Act: -0.1700
Data Index: 7651299 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7929. Min Range: -5.7929
Max Act: 5.2304. Min Act: -0.1700
Data Index: 7815874 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #19