Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3826 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1845. Min Range: -6.1845
Max Act: 6.1845. Min Act: -0.1700
Data Index: 8624241 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1845. Min Range: -6.1845
Max Act: 6.0907. Min Act: -0.1700
Data Index: 173877 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1845. Min Range: -6.1845
Max Act: 6.0595. Min Act: -0.1700
Data Index: 1231941 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1845. Min Range: -6.1845
Max Act: 5.9970. Min Act: -0.1700
Data Index: 4135514 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1845. Min Range: -6.1845
Max Act: 5.9970. Min Act: -0.1700
Data Index: 1944873 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1845. Min Range: -6.1845
Max Act: 5.9657. Min Act: -0.1700
Data Index: 4079328 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1845. Min Range: -6.1845
Max Act: 5.9345. Min Act: -0.1700
Data Index: 1802677 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1845. Min Range: -6.1845
Max Act: 5.9345. Min Act: -0.1700
Data Index: 5674019 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1845. Min Range: -6.1845
Max Act: 5.9345. Min Act: -0.1700
Data Index: 7506453 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1845. Min Range: -6.1845
Max Act: 5.9032. Min Act: -0.1700
Data Index: 3630349 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1845. Min Range: -6.1845
Max Act: 5.8720. Min Act: -0.1700
Data Index: 1320198 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1845. Min Range: -6.1845
Max Act: 5.8720. Min Act: -0.1700
Data Index: 669922 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1845. Min Range: -6.1845
Max Act: 5.8407. Min Act: -0.1700
Data Index: 5484984 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1845. Min Range: -6.1845
Max Act: 5.8095. Min Act: -0.1700
Data Index: 785375 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1845. Min Range: -6.1845
Max Act: 5.8407. Min Act: -0.1700
Data Index: 7622568 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1845. Min Range: -6.1845
Max Act: 5.8407. Min Act: -0.1700
Data Index: 1576986 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1845. Min Range: -6.1845
Max Act: 5.8095. Min Act: -0.1700
Data Index: 8654685 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1845. Min Range: -6.1845
Max Act: 5.7782. Min Act: -0.1700
Data Index: 7958635 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1845. Min Range: -6.1845
Max Act: 5.8095. Min Act: -0.1700
Data Index: 6237609 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1845. Min Range: -6.1845
Max Act: 5.8095. Min Act: -0.1700
Data Index: 790209 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #19