Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1513 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6777. Min Range: -5.6777
Max Act: 5.6777. Min Act: -0.1700
Data Index: 6748686 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6777. Min Range: -5.6777
Max Act: 5.0839. Min Act: -0.1700
Data Index: 5678255 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6777. Min Range: -5.6777
Max Act: 5.0214. Min Act: -0.1700
Data Index: 1189007 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6777. Min Range: -5.6777
Max Act: 4.8964. Min Act: -0.1700
Data Index: 5049809 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6777. Min Range: -5.6777
Max Act: 4.8964. Min Act: -0.1700
Data Index: 3502014 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6777. Min Range: -5.6777
Max Act: 4.8652. Min Act: -0.1700
Data Index: 5389534 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6777. Min Range: -5.6777
Max Act: 4.7402. Min Act: -0.1700
Data Index: 6094942 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6777. Min Range: -5.6777
Max Act: 4.7402. Min Act: -0.1700
Data Index: 1712374 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6777. Min Range: -5.6777
Max Act: 4.7089. Min Act: -0.1700
Data Index: 700062 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6777. Min Range: -5.6777
Max Act: 4.6464. Min Act: -0.1700
Data Index: 2972327 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6777. Min Range: -5.6777
Max Act: 4.6777. Min Act: -0.1700
Data Index: 3606812 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6777. Min Range: -5.6777
Max Act: 4.7089. Min Act: -0.1700
Data Index: 3930892 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6777. Min Range: -5.6777
Max Act: 4.6464. Min Act: -0.1700
Data Index: 8444616 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6777. Min Range: -5.6777
Max Act: 4.6464. Min Act: -0.1700
Data Index: 8775641 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6777. Min Range: -5.6777
Max Act: 4.6464. Min Act: -0.1700
Data Index: 333650 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6777. Min Range: -5.6777
Max Act: 4.6464. Min Act: -0.1700
Data Index: 7416536 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6777. Min Range: -5.6777
Max Act: 4.6152. Min Act: -0.1700
Data Index: 7940243 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6777. Min Range: -5.6777
Max Act: 4.6152. Min Act: -0.1700
Data Index: 1216284 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6777. Min Range: -5.6777
Max Act: 4.5839. Min Act: -0.1700
Data Index: 15841 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6777. Min Range: -5.6777
Max Act: 4.6152. Min Act: -0.1700
Data Index: 4971062 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #19