Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3561 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6439. Min Range: -7.6439
Max Act: 7.6439. Min Act: -0.1700
Data Index: 7696852 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6439. Min Range: -7.6439
Max Act: 7.5189. Min Act: -0.1700
Data Index: 5412799 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6439. Min Range: -7.6439
Max Act: 7.4564. Min Act: -0.1700
Data Index: 7041791 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6439. Min Range: -7.6439
Max Act: 7.1752. Min Act: -0.1700
Data Index: 4391848 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6439. Min Range: -7.6439
Max Act: 7.1439. Min Act: -0.1700
Data Index: 3204422 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6439. Min Range: -7.6439
Max Act: 7.1127. Min Act: -0.1700
Data Index: 2832745 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6439. Min Range: -7.6439
Max Act: 7.0502. Min Act: -0.1700
Data Index: 6431990 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6439. Min Range: -7.6439
Max Act: 7.0189. Min Act: -0.1700
Data Index: 8165291 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6439. Min Range: -7.6439
Max Act: 6.9564. Min Act: -0.1700
Data Index: 4431967 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6439. Min Range: -7.6439
Max Act: 6.9252. Min Act: -0.1700
Data Index: 7531557 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6439. Min Range: -7.6439
Max Act: 6.8939. Min Act: -0.1700
Data Index: 1256838 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6439. Min Range: -7.6439
Max Act: 6.8939. Min Act: -0.1700
Data Index: 6140404 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6439. Min Range: -7.6439
Max Act: 6.8627. Min Act: -0.1700
Data Index: 2296608 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6439. Min Range: -7.6439
Max Act: 6.8939. Min Act: -0.1700
Data Index: 2211047 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6439. Min Range: -7.6439
Max Act: 6.8627. Min Act: -0.1700
Data Index: 7531564 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6439. Min Range: -7.6439
Max Act: 6.8627. Min Act: -0.1700
Data Index: 3089087 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6439. Min Range: -7.6439
Max Act: 6.8627. Min Act: -0.1700
Data Index: 7888507 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6439. Min Range: -7.6439
Max Act: 6.8627. Min Act: -0.1700
Data Index: 6024042 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6439. Min Range: -7.6439
Max Act: 6.8627. Min Act: -0.1700
Data Index: 7531558 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6439. Min Range: -7.6439
Max Act: 6.8002. Min Act: -0.1700
Data Index: 8152542 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #19