Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3925 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6439. Min Range: -5.6439
Max Act: 5.6439. Min Act: -0.1700
Data Index: 7610246 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6439. Min Range: -5.6439
Max Act: 5.6126. Min Act: -0.1700
Data Index: 8374684 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6439. Min Range: -5.6439
Max Act: 5.5814. Min Act: -0.1700
Data Index: 3328886 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6439. Min Range: -5.6439
Max Act: 5.5189. Min Act: -0.1700
Data Index: 7256929 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6439. Min Range: -5.6439
Max Act: 5.5501. Min Act: -0.1700
Data Index: 7488502 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6439. Min Range: -5.6439
Max Act: 5.5189. Min Act: -0.1700
Data Index: 2947384 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6439. Min Range: -5.6439
Max Act: 5.4876. Min Act: -0.1700
Data Index: 3994167 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6439. Min Range: -5.6439
Max Act: 5.4876. Min Act: -0.1700
Data Index: 1427970 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6439. Min Range: -5.6439
Max Act: 5.4876. Min Act: -0.1700
Data Index: 6710035 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6439. Min Range: -5.6439
Max Act: 5.4876. Min Act: -0.1700
Data Index: 8099563 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6439. Min Range: -5.6439
Max Act: 5.5189. Min Act: -0.1700
Data Index: 7870272 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6439. Min Range: -5.6439
Max Act: 5.4876. Min Act: -0.1700
Data Index: 5904766 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6439. Min Range: -5.6439
Max Act: 5.4876. Min Act: -0.1700
Data Index: 2195561 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6439. Min Range: -5.6439
Max Act: 5.4564. Min Act: -0.1700
Data Index: 7349244 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6439. Min Range: -5.6439
Max Act: 5.4251. Min Act: -0.1700
Data Index: 349366 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6439. Min Range: -5.6439
Max Act: 5.4564. Min Act: -0.1700
Data Index: 5996981 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6439. Min Range: -5.6439
Max Act: 5.4564. Min Act: -0.1700
Data Index: 7489359 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6439. Min Range: -5.6439
Max Act: 5.4564. Min Act: -0.1700
Data Index: 4590523 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6439. Min Range: -5.6439
Max Act: 5.4251. Min Act: -0.1700
Data Index: 5556100 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6439. Min Range: -5.6439
Max Act: 5.4251. Min Act: -0.1700
Data Index: 6914968 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #19