Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3629 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2214. Min Range: -5.2214
Max Act: 5.2214. Min Act: -0.1700
Data Index: 1621861 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2214. Min Range: -5.2214
Max Act: 4.8777. Min Act: -0.1700
Data Index: 221782 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2214. Min Range: -5.2214
Max Act: 4.8464. Min Act: -0.1700
Data Index: 152773 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2214. Min Range: -5.2214
Max Act: 4.8464. Min Act: -0.1700
Data Index: 530202 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2214. Min Range: -5.2214
Max Act: 4.8152. Min Act: -0.1700
Data Index: 3123352 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2214. Min Range: -5.2214
Max Act: 4.8152. Min Act: -0.1700
Data Index: 6731306 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2214. Min Range: -5.2214
Max Act: 4.8152. Min Act: -0.1700
Data Index: 3982223 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2214. Min Range: -5.2214
Max Act: 4.8152. Min Act: -0.1700
Data Index: 5457598 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2214. Min Range: -5.2214
Max Act: 4.8152. Min Act: -0.1700
Data Index: 6982382 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2214. Min Range: -5.2214
Max Act: 4.8152. Min Act: -0.1700
Data Index: 2688013 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2214. Min Range: -5.2214
Max Act: 4.8152. Min Act: -0.1700
Data Index: 7834064 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2214. Min Range: -5.2214
Max Act: 4.7839. Min Act: -0.1700
Data Index: 272610 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2214. Min Range: -5.2214
Max Act: 4.7839. Min Act: -0.1700
Data Index: 4997914 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2214. Min Range: -5.2214
Max Act: 4.7839. Min Act: -0.1700
Data Index: 4744553 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2214. Min Range: -5.2214
Max Act: 4.7527. Min Act: -0.1700
Data Index: 7369560 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2214. Min Range: -5.2214
Max Act: 4.7527. Min Act: -0.1700
Data Index: 5575041 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2214. Min Range: -5.2214
Max Act: 4.7527. Min Act: -0.1700
Data Index: 7320252 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2214. Min Range: -5.2214
Max Act: 4.7527. Min Act: -0.1700
Data Index: 1126523 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2214. Min Range: -5.2214
Max Act: 4.7214. Min Act: -0.1700
Data Index: 857640 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2214. Min Range: -5.2214
Max Act: 4.7214. Min Act: -0.1700
Data Index: 8862 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #19