Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2043 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1352. Min Range: -5.1352
Max Act: 5.1352. Min Act: -0.1700
Data Index: 2266731 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1352. Min Range: -5.1352
Max Act: 5.0102. Min Act: -0.1700
Data Index: 5554719 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1352. Min Range: -5.1352
Max Act: 5.0415. Min Act: -0.1700
Data Index: 6986631 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1352. Min Range: -5.1352
Max Act: 5.0415. Min Act: -0.1700
Data Index: 5475065 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1352. Min Range: -5.1352
Max Act: 5.0102. Min Act: -0.1700
Data Index: 548883 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1352. Min Range: -5.1352
Max Act: 4.9477. Min Act: -0.1700
Data Index: 6803473 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1352. Min Range: -5.1352
Max Act: 4.8852. Min Act: -0.1700
Data Index: 4736800 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1352. Min Range: -5.1352
Max Act: 4.8227. Min Act: -0.1700
Data Index: 7333677 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1352. Min Range: -5.1352
Max Act: 4.7915. Min Act: -0.1700
Data Index: 3894147 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1352. Min Range: -5.1352
Max Act: 4.7602. Min Act: -0.1700
Data Index: 4711861 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1352. Min Range: -5.1352
Max Act: 4.7602. Min Act: -0.1700
Data Index: 8053389 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1352. Min Range: -5.1352
Max Act: 4.7290. Min Act: -0.1700
Data Index: 5996641 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1352. Min Range: -5.1352
Max Act: 4.7290. Min Act: -0.1700
Data Index: 1878441 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1352. Min Range: -5.1352
Max Act: 4.7602. Min Act: -0.1700
Data Index: 7000753 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1352. Min Range: -5.1352
Max Act: 4.6665. Min Act: -0.1700
Data Index: 216760 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1352. Min Range: -5.1352
Max Act: 4.6665. Min Act: -0.1700
Data Index: 4820353 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1352. Min Range: -5.1352
Max Act: 4.6665. Min Act: -0.1700
Data Index: 345540 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1352. Min Range: -5.1352
Max Act: 4.6665. Min Act: -0.1700
Data Index: 870925 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1352. Min Range: -5.1352
Max Act: 4.6352. Min Act: -0.1700
Data Index: 6323431 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1352. Min Range: -5.1352
Max Act: 4.6352. Min Act: -0.1700
Data Index: 4392324 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #19