Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2344 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4020. Min Range: -6.4020
Max Act: 6.4020. Min Act: -0.1700
Data Index: 1531917 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4020. Min Range: -6.4020
Max Act: 6.2458. Min Act: -0.1700
Data Index: 5584235 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4020. Min Range: -6.4020
Max Act: 6.0895. Min Act: -0.1700
Data Index: 350482 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4020. Min Range: -6.4020
Max Act: 6.0895. Min Act: -0.1700
Data Index: 7964761 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4020. Min Range: -6.4020
Max Act: 6.0895. Min Act: -0.1700
Data Index: 6131375 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4020. Min Range: -6.4020
Max Act: 6.0270. Min Act: -0.1700
Data Index: 3721522 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4020. Min Range: -6.4020
Max Act: 5.9958. Min Act: -0.1700
Data Index: 490733 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4020. Min Range: -6.4020
Max Act: 5.9645. Min Act: -0.1700
Data Index: 3012808 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4020. Min Range: -6.4020
Max Act: 5.9645. Min Act: -0.1700
Data Index: 695692 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4020. Min Range: -6.4020
Max Act: 5.8708. Min Act: -0.1700
Data Index: 6955031 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4020. Min Range: -6.4020
Max Act: 5.8708. Min Act: -0.1700
Data Index: 4369235 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4020. Min Range: -6.4020
Max Act: 5.8708. Min Act: -0.1700
Data Index: 7800372 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4020. Min Range: -6.4020
Max Act: 5.8395. Min Act: -0.1700
Data Index: 8122297 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4020. Min Range: -6.4020
Max Act: 5.8395. Min Act: -0.1700
Data Index: 3365387 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4020. Min Range: -6.4020
Max Act: 5.8395. Min Act: -0.1700
Data Index: 5190822 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4020. Min Range: -6.4020
Max Act: 5.8083. Min Act: -0.1700
Data Index: 7060020 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4020. Min Range: -6.4020
Max Act: 5.8395. Min Act: -0.1700
Data Index: 211597 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4020. Min Range: -6.4020
Max Act: 5.7770. Min Act: -0.1700
Data Index: 7474290 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4020. Min Range: -6.4020
Max Act: 5.7770. Min Act: -0.1700
Data Index: 6794206 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4020. Min Range: -6.4020
Max Act: 5.7458. Min Act: -0.1700
Data Index: 5204579 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #19