Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4008 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6180. Min Range: -5.6180
Max Act: 5.6180. Min Act: -0.1700
Data Index: 1369195 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6180. Min Range: -5.6180
Max Act: 5.5555. Min Act: -0.1700
Data Index: 3257165 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6180. Min Range: -5.6180
Max Act: 5.5243. Min Act: -0.1700
Data Index: 8249347 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6180. Min Range: -5.6180
Max Act: 5.4305. Min Act: -0.1700
Data Index: 772899 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6180. Min Range: -5.6180
Max Act: 5.4618. Min Act: -0.1700
Data Index: 8123578 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6180. Min Range: -5.6180
Max Act: 5.3368. Min Act: -0.1700
Data Index: 5788589 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6180. Min Range: -5.6180
Max Act: 5.3680. Min Act: -0.1700
Data Index: 5915319 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6180. Min Range: -5.6180
Max Act: 5.3680. Min Act: -0.1700
Data Index: 4915301 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6180. Min Range: -5.6180
Max Act: 5.3368. Min Act: -0.1700
Data Index: 3616644 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6180. Min Range: -5.6180
Max Act: 5.3368. Min Act: -0.1700
Data Index: 3986256 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6180. Min Range: -5.6180
Max Act: 5.3055. Min Act: -0.1700
Data Index: 7228590 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6180. Min Range: -5.6180
Max Act: 5.2743. Min Act: -0.1700
Data Index: 2757099 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6180. Min Range: -5.6180
Max Act: 5.2743. Min Act: -0.1700
Data Index: 7209411 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6180. Min Range: -5.6180
Max Act: 5.2430. Min Act: -0.1700
Data Index: 627641 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6180. Min Range: -5.6180
Max Act: 5.2430. Min Act: -0.1700
Data Index: 7712170 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6180. Min Range: -5.6180
Max Act: 5.2118. Min Act: -0.1700
Data Index: 3121413 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6180. Min Range: -5.6180
Max Act: 5.2118. Min Act: -0.1700
Data Index: 381336 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6180. Min Range: -5.6180
Max Act: 5.1805. Min Act: -0.1700
Data Index: 6286606 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6180. Min Range: -5.6180
Max Act: 5.1805. Min Act: -0.1700
Data Index: 4355380 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6180. Min Range: -5.6180
Max Act: 5.1805. Min Act: -0.1700
Data Index: 983867 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #19