Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1915 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9337. Min Range: -5.9337
Max Act: 5.9337. Min Act: -0.1700
Data Index: 2777023 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9337. Min Range: -5.9337
Max Act: 5.9024. Min Act: -0.1700
Data Index: 8704605 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9337. Min Range: -5.9337
Max Act: 5.8087. Min Act: -0.1700
Data Index: 7577219 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9337. Min Range: -5.9337
Max Act: 5.7462. Min Act: -0.1700
Data Index: 1407196 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9337. Min Range: -5.9337
Max Act: 5.7774. Min Act: -0.1700
Data Index: 6830875 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9337. Min Range: -5.9337
Max Act: 5.6837. Min Act: -0.1700
Data Index: 4701405 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9337. Min Range: -5.9337
Max Act: 5.6837. Min Act: -0.1700
Data Index: 5615587 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9337. Min Range: -5.9337
Max Act: 5.6524. Min Act: -0.1700
Data Index: 7021558 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9337. Min Range: -5.9337
Max Act: 5.5587. Min Act: -0.1700
Data Index: 8342919 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9337. Min Range: -5.9337
Max Act: 5.5274. Min Act: -0.1700
Data Index: 1241590 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9337. Min Range: -5.9337
Max Act: 5.5274. Min Act: -0.1700
Data Index: 5918356 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9337. Min Range: -5.9337
Max Act: 5.5274. Min Act: -0.1700
Data Index: 3130810 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9337. Min Range: -5.9337
Max Act: 5.5274. Min Act: -0.1700
Data Index: 523502 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9337. Min Range: -5.9337
Max Act: 5.4962. Min Act: -0.1700
Data Index: 7479885 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9337. Min Range: -5.9337
Max Act: 5.4962. Min Act: -0.1700
Data Index: 2633561 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9337. Min Range: -5.9337
Max Act: 5.4649. Min Act: -0.1700
Data Index: 3211557 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9337. Min Range: -5.9337
Max Act: 5.4337. Min Act: -0.1700
Data Index: 5787084 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9337. Min Range: -5.9337
Max Act: 5.4649. Min Act: -0.1700
Data Index: 7055929 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9337. Min Range: -5.9337
Max Act: 5.4337. Min Act: -0.1700
Data Index: 4794275 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9337. Min Range: -5.9337
Max Act: 5.4337. Min Act: -0.1700
Data Index: 6173938 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #19