Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 978 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.7931. Min Range: -4.7931
Max Act: 4.7931. Min Act: -0.1700
Data Index: 7246929 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7931. Min Range: -4.7931
Max Act: 4.6681. Min Act: -0.1700
Data Index: 5679047 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7931. Min Range: -4.7931
Max Act: 4.5118. Min Act: -0.1700
Data Index: 5679046 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7931. Min Range: -4.7931
Max Act: 4.4493. Min Act: -0.1700
Data Index: 5405592 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7931. Min Range: -4.7931
Max Act: 4.4181. Min Act: -0.1700
Data Index: 7652585 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7931. Min Range: -4.7931
Max Act: 4.4181. Min Act: -0.1700
Data Index: 3911912 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7931. Min Range: -4.7931
Max Act: 4.4181. Min Act: -0.1700
Data Index: 8571173 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7931. Min Range: -4.7931
Max Act: 4.3868. Min Act: -0.1700
Data Index: 7974668 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7931. Min Range: -4.7931
Max Act: 4.3868. Min Act: -0.1700
Data Index: 4973925 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7931. Min Range: -4.7931
Max Act: 4.3868. Min Act: -0.1700
Data Index: 7832463 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7931. Min Range: -4.7931
Max Act: 4.3556. Min Act: -0.1700
Data Index: 7982772 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7931. Min Range: -4.7931
Max Act: 4.3556. Min Act: -0.1700
Data Index: 7798842 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7931. Min Range: -4.7931
Max Act: 4.3556. Min Act: -0.1700
Data Index: 2900928 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7931. Min Range: -4.7931
Max Act: 4.3243. Min Act: -0.1700
Data Index: 7524681 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7931. Min Range: -4.7931
Max Act: 4.2931. Min Act: -0.1700
Data Index: 954801 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7931. Min Range: -4.7931
Max Act: 4.3243. Min Act: -0.1700
Data Index: 6005862 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7931. Min Range: -4.7931
Max Act: 4.3243. Min Act: -0.1700
Data Index: 3959281 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7931. Min Range: -4.7931
Max Act: 4.3243. Min Act: -0.1700
Data Index: 5800907 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7931. Min Range: -4.7931
Max Act: 4.3243. Min Act: -0.1700
Data Index: 2589067 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7931. Min Range: -4.7931
Max Act: 4.2931. Min Act: -0.1700
Data Index: 4946358 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #19