Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4902 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9694. Min Range: -5.9694
Max Act: 5.9694. Min Act: -0.1700
Data Index: 199004 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9694. Min Range: -5.9694
Max Act: 5.9069. Min Act: -0.1700
Data Index: 7464546 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9694. Min Range: -5.9694
Max Act: 5.9382. Min Act: -0.1700
Data Index: 4318479 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9694. Min Range: -5.9694
Max Act: 5.8757. Min Act: -0.1700
Data Index: 2956204 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9694. Min Range: -5.9694
Max Act: 5.9069. Min Act: -0.1700
Data Index: 464274 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9694. Min Range: -5.9694
Max Act: 5.9069. Min Act: -0.1700
Data Index: 3180526 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9694. Min Range: -5.9694
Max Act: 5.8444. Min Act: -0.1700
Data Index: 8807497 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9694. Min Range: -5.9694
Max Act: 5.8757. Min Act: -0.1700
Data Index: 5453084 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9694. Min Range: -5.9694
Max Act: 5.8444. Min Act: -0.1700
Data Index: 3572504 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9694. Min Range: -5.9694
Max Act: 5.8444. Min Act: -0.1700
Data Index: 5589457 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9694. Min Range: -5.9694
Max Act: 5.7819. Min Act: -0.1700
Data Index: 7414310 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9694. Min Range: -5.9694
Max Act: 5.7819. Min Act: -0.1700
Data Index: 184464 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9694. Min Range: -5.9694
Max Act: 5.8132. Min Act: -0.1700
Data Index: 6488668 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9694. Min Range: -5.9694
Max Act: 5.7819. Min Act: -0.1700
Data Index: 1872615 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9694. Min Range: -5.9694
Max Act: 5.7819. Min Act: -0.1700
Data Index: 1594729 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9694. Min Range: -5.9694
Max Act: 5.7819. Min Act: -0.1700
Data Index: 6404183 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9694. Min Range: -5.9694
Max Act: 5.7194. Min Act: -0.1700
Data Index: 893337 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9694. Min Range: -5.9694
Max Act: 5.7194. Min Act: -0.1700
Data Index: 3050778 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9694. Min Range: -5.9694
Max Act: 5.7194. Min Act: -0.1700
Data Index: 4894917 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9694. Min Range: -5.9694
Max Act: 5.7194. Min Act: -0.1700
Data Index: 947137 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #19