Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3570 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4256. Min Range: -7.4256
Max Act: 7.4256. Min Act: -0.1700
Data Index: 5024455 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4256. Min Range: -7.4256
Max Act: 7.2694. Min Act: -0.1700
Data Index: 3385225 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4256. Min Range: -7.4256
Max Act: 7.1756. Min Act: -0.1700
Data Index: 2818652 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4256. Min Range: -7.4256
Max Act: 7.1444. Min Act: -0.1700
Data Index: 8141222 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4256. Min Range: -7.4256
Max Act: 7.1131. Min Act: -0.1700
Data Index: 3767732 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4256. Min Range: -7.4256
Max Act: 7.1131. Min Act: -0.1700
Data Index: 2538816 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4256. Min Range: -7.4256
Max Act: 7.0506. Min Act: -0.1700
Data Index: 2107065 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4256. Min Range: -7.4256
Max Act: 6.9881. Min Act: -0.1700
Data Index: 2125891 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4256. Min Range: -7.4256
Max Act: 6.9569. Min Act: -0.1700
Data Index: 1001876 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4256. Min Range: -7.4256
Max Act: 6.9569. Min Act: -0.1700
Data Index: 3355731 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4256. Min Range: -7.4256
Max Act: 6.9569. Min Act: -0.1700
Data Index: 1782999 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4256. Min Range: -7.4256
Max Act: 6.9256. Min Act: -0.1700
Data Index: 3321463 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4256. Min Range: -7.4256
Max Act: 6.8631. Min Act: -0.1700
Data Index: 4655518 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4256. Min Range: -7.4256
Max Act: 6.8319. Min Act: -0.1700
Data Index: 3790396 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4256. Min Range: -7.4256
Max Act: 6.8319. Min Act: -0.1700
Data Index: 7845118 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4256. Min Range: -7.4256
Max Act: 6.8319. Min Act: -0.1700
Data Index: 5667869 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4256. Min Range: -7.4256
Max Act: 6.8006. Min Act: -0.1700
Data Index: 3198899 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4256. Min Range: -7.4256
Max Act: 6.7694. Min Act: -0.1700
Data Index: 5398053 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4256. Min Range: -7.4256
Max Act: 6.8319. Min Act: -0.1700
Data Index: 4089228 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4256. Min Range: -7.4256
Max Act: 6.8006. Min Act: -0.1700
Data Index: 2805872 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #19