Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5383 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9725. Min Range: -3.9725
Max Act: 3.9725. Min Act: -0.1700
Data Index: 8198182 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9725. Min Range: -3.9725
Max Act: 3.8162. Min Act: -0.1700
Data Index: 3648660 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9725. Min Range: -3.9725
Max Act: 3.8162. Min Act: -0.1700
Data Index: 271254 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9725. Min Range: -3.9725
Max Act: 3.7536. Min Act: -0.1700
Data Index: 3565495 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9725. Min Range: -3.9725
Max Act: 3.7380. Min Act: -0.1700
Data Index: 5967267 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9725. Min Range: -3.9725
Max Act: 3.7380. Min Act: -0.1700
Data Index: 5994130 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9725. Min Range: -3.9725
Max Act: 3.6910. Min Act: -0.1700
Data Index: 365950 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9725. Min Range: -3.9725
Max Act: 3.6910. Min Act: -0.1700
Data Index: 3274614 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9725. Min Range: -3.9725
Max Act: 3.6441. Min Act: -0.1700
Data Index: 7059537 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9725. Min Range: -3.9725
Max Act: 3.6598. Min Act: -0.1700
Data Index: 375788 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9725. Min Range: -3.9725
Max Act: 3.6128. Min Act: -0.1700
Data Index: 2287642 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9725. Min Range: -3.9725
Max Act: 3.5972. Min Act: -0.1700
Data Index: 4224372 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9725. Min Range: -3.9725
Max Act: 3.5972. Min Act: -0.1700
Data Index: 7634127 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9725. Min Range: -3.9725
Max Act: 3.5972. Min Act: -0.1700
Data Index: 6340613 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9725. Min Range: -3.9725
Max Act: 3.5815. Min Act: -0.1700
Data Index: 4125482 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9725. Min Range: -3.9725
Max Act: 3.5659. Min Act: -0.1700
Data Index: 5598091 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9725. Min Range: -3.9725
Max Act: 3.5345. Min Act: -0.1700
Data Index: 8658015 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9725. Min Range: -3.9725
Max Act: 3.5345. Min Act: -0.1700
Data Index: 1508152 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9725. Min Range: -3.9725
Max Act: 3.5345. Min Act: -0.1700
Data Index: 3001473 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9725. Min Range: -3.9725
Max Act: 3.5189. Min Act: -0.1700
Data Index: 3845285 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #19