Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 876 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.9354. Min Range: -3.9354
Max Act: 3.9354. Min Act: -0.1700
Data Index: 8427289 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9354. Min Range: -3.9354
Max Act: 3.9354. Min Act: -0.1700
Data Index: 8427279 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9354. Min Range: -3.9354
Max Act: 3.9041. Min Act: -0.1700
Data Index: 1573946 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9354. Min Range: -3.9354
Max Act: 3.8728. Min Act: -0.1700
Data Index: 2875021 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9354. Min Range: -3.9354
Max Act: 3.8728. Min Act: -0.1700
Data Index: 8806826 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9354. Min Range: -3.9354
Max Act: 3.8259. Min Act: -0.1700
Data Index: 4793278 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9354. Min Range: -3.9354
Max Act: 3.8416. Min Act: -0.1700
Data Index: 4899084 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9354. Min Range: -3.9354
Max Act: 3.7634. Min Act: -0.1700
Data Index: 6243266 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9354. Min Range: -3.9354
Max Act: 3.7947. Min Act: -0.1700
Data Index: 8803622 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9354. Min Range: -3.9354
Max Act: 3.7634. Min Act: -0.1700
Data Index: 8439074 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9354. Min Range: -3.9354
Max Act: 3.7477. Min Act: -0.1700
Data Index: 8031914 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9354. Min Range: -3.9354
Max Act: 3.7477. Min Act: -0.1700
Data Index: 3652091 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9354. Min Range: -3.9354
Max Act: 3.7321. Min Act: -0.1700
Data Index: 375976 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9354. Min Range: -3.9354
Max Act: 3.7321. Min Act: -0.1700
Data Index: 360381 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9354. Min Range: -3.9354
Max Act: 3.7165. Min Act: -0.1700
Data Index: 1048228 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9354. Min Range: -3.9354
Max Act: 3.7165. Min Act: -0.1700
Data Index: 4111113 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9354. Min Range: -3.9354
Max Act: 3.7008. Min Act: -0.1700
Data Index: 2308537 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9354. Min Range: -3.9354
Max Act: 3.7165. Min Act: -0.1700
Data Index: 27752 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9354. Min Range: -3.9354
Max Act: 3.7165. Min Act: -0.1700
Data Index: 2157413 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9354. Min Range: -3.9354
Max Act: 3.7165. Min Act: -0.1700
Data Index: 8815121 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #19