Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1555 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.4539. Min Range: -4.4539
Max Act: 4.4539. Min Act: -0.1700
Data Index: 679219 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4539. Min Range: -4.4539
Max Act: 4.2976. Min Act: -0.1700
Data Index: 3297432 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4539. Min Range: -4.4539
Max Act: 4.2039. Min Act: -0.1700
Data Index: 6761012 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4539. Min Range: -4.4539
Max Act: 4.2039. Min Act: -0.1700
Data Index: 4310355 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4539. Min Range: -4.4539
Max Act: 4.1101. Min Act: -0.1700
Data Index: 2018548 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4539. Min Range: -4.4539
Max Act: 4.0163. Min Act: -0.1700
Data Index: 3538974 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4539. Min Range: -4.4539
Max Act: 3.9538. Min Act: -0.1700
Data Index: 4242691 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4539. Min Range: -4.4539
Max Act: 3.9538. Min Act: -0.1700
Data Index: 7452522 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4539. Min Range: -4.4539
Max Act: 3.9226. Min Act: -0.1700
Data Index: 6448394 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4539. Min Range: -4.4539
Max Act: 3.9538. Min Act: -0.1700
Data Index: 6565216 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4539. Min Range: -4.4539
Max Act: 3.9538. Min Act: -0.1700
Data Index: 8007386 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4539. Min Range: -4.4539
Max Act: 3.9226. Min Act: -0.1700
Data Index: 2323739 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4539. Min Range: -4.4539
Max Act: 3.8913. Min Act: -0.1700
Data Index: 5135089 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4539. Min Range: -4.4539
Max Act: 3.9226. Min Act: -0.1700
Data Index: 1754206 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4539. Min Range: -4.4539
Max Act: 3.8913. Min Act: -0.1700
Data Index: 6984191 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4539. Min Range: -4.4539
Max Act: 3.8913. Min Act: -0.1700
Data Index: 6186351 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4539. Min Range: -4.4539
Max Act: 3.8288. Min Act: -0.1700
Data Index: 4258515 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4539. Min Range: -4.4539
Max Act: 3.8288. Min Act: -0.1700
Data Index: 1363966 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4539. Min Range: -4.4539
Max Act: 3.8288. Min Act: -0.1700
Data Index: 722994 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4539. Min Range: -4.4539
Max Act: 3.8600. Min Act: -0.1700
Data Index: 5362768 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #19