Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1249 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.8852. Min Range: -5.8852
Max Act: 5.8852. Min Act: -0.1700
Data Index: 1486783 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8852. Min Range: -5.8852
Max Act: 5.8227. Min Act: -0.1700
Data Index: 2498090 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8852. Min Range: -5.8852
Max Act: 5.7915. Min Act: -0.1700
Data Index: 6719211 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8852. Min Range: -5.8852
Max Act: 5.6977. Min Act: -0.1700
Data Index: 5563822 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8852. Min Range: -5.8852
Max Act: 5.6665. Min Act: -0.1700
Data Index: 7841765 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8852. Min Range: -5.8852
Max Act: 5.6352. Min Act: -0.1700
Data Index: 541752 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8852. Min Range: -5.8852
Max Act: 5.6352. Min Act: -0.1700
Data Index: 1616872 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8852. Min Range: -5.8852
Max Act: 5.6352. Min Act: -0.1700
Data Index: 4028695 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8852. Min Range: -5.8852
Max Act: 5.6040. Min Act: -0.1700
Data Index: 5001393 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8852. Min Range: -5.8852
Max Act: 5.6040. Min Act: -0.1700
Data Index: 3511424 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8852. Min Range: -5.8852
Max Act: 5.6040. Min Act: -0.1700
Data Index: 2214127 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8852. Min Range: -5.8852
Max Act: 5.6352. Min Act: -0.1700
Data Index: 211449 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8852. Min Range: -5.8852
Max Act: 5.5415. Min Act: -0.1700
Data Index: 1594186 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8852. Min Range: -5.8852
Max Act: 5.5415. Min Act: -0.1700
Data Index: 6683403 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8852. Min Range: -5.8852
Max Act: 5.5415. Min Act: -0.1700
Data Index: 7540545 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8852. Min Range: -5.8852
Max Act: 5.5415. Min Act: -0.1700
Data Index: 1434095 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8852. Min Range: -5.8852
Max Act: 5.5415. Min Act: -0.1700
Data Index: 3459195 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8852. Min Range: -5.8852
Max Act: 5.5102. Min Act: -0.1700
Data Index: 6184881 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8852. Min Range: -5.8852
Max Act: 5.4790. Min Act: -0.1700
Data Index: 5552380 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8852. Min Range: -5.8852
Max Act: 5.5102. Min Act: -0.1700
Data Index: 3408846 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #19