Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1503 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.9022. Min Range: -4.9022
Max Act: 4.8709. Min Act: -0.1700
Data Index: 4309674 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9022. Min Range: -4.9022
Max Act: 4.9022. Min Act: -0.1700
Data Index: 1739653 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9022. Min Range: -4.9022
Max Act: 4.8084. Min Act: -0.1700
Data Index: 839449 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9022. Min Range: -4.9022
Max Act: 4.6522. Min Act: -0.1700
Data Index: 8307918 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9022. Min Range: -4.9022
Max Act: 4.6209. Min Act: -0.1700
Data Index: 6509930 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9022. Min Range: -4.9022
Max Act: 4.5897. Min Act: -0.1700
Data Index: 3230892 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9022. Min Range: -4.9022
Max Act: 4.5897. Min Act: -0.1700
Data Index: 7744402 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9022. Min Range: -4.9022
Max Act: 4.5584. Min Act: -0.1700
Data Index: 5737647 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9022. Min Range: -4.9022
Max Act: 4.5897. Min Act: -0.1700
Data Index: 213053 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9022. Min Range: -4.9022
Max Act: 4.5584. Min Act: -0.1700
Data Index: 1835288 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9022. Min Range: -4.9022
Max Act: 4.5584. Min Act: -0.1700
Data Index: 4726381 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9022. Min Range: -4.9022
Max Act: 4.5584. Min Act: -0.1700
Data Index: 553545 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9022. Min Range: -4.9022
Max Act: 4.5272. Min Act: -0.1700
Data Index: 49068 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9022. Min Range: -4.9022
Max Act: 4.4959. Min Act: -0.1700
Data Index: 3876688 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9022. Min Range: -4.9022
Max Act: 4.5272. Min Act: -0.1700
Data Index: 7627662 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9022. Min Range: -4.9022
Max Act: 4.5272. Min Act: -0.1700
Data Index: 6824303 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9022. Min Range: -4.9022
Max Act: 4.4959. Min Act: -0.1700
Data Index: 6333340 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9022. Min Range: -4.9022
Max Act: 4.4647. Min Act: -0.1700
Data Index: 6072413 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9022. Min Range: -4.9022
Max Act: 4.4959. Min Act: -0.1700
Data Index: 4131281 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9022. Min Range: -4.9022
Max Act: 4.4959. Min Act: -0.1700
Data Index: 49069 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #19