Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3591 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.3476. Min Range: -6.3476
Max Act: 6.3476. Min Act: -0.1700
Data Index: 1221296 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3476. Min Range: -6.3476
Max Act: 6.2851. Min Act: -0.1700
Data Index: 4720628 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3476. Min Range: -6.3476
Max Act: 6.2538. Min Act: -0.1700
Data Index: 7290133 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3476. Min Range: -6.3476
Max Act: 6.2538. Min Act: -0.1700
Data Index: 6220062 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3476. Min Range: -6.3476
Max Act: 6.2226. Min Act: -0.1700
Data Index: 7087582 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3476. Min Range: -6.3476
Max Act: 6.2226. Min Act: -0.1700
Data Index: 2523039 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3476. Min Range: -6.3476
Max Act: 6.2226. Min Act: -0.1700
Data Index: 5364305 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3476. Min Range: -6.3476
Max Act: 6.2226. Min Act: -0.1700
Data Index: 1868712 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3476. Min Range: -6.3476
Max Act: 6.1913. Min Act: -0.1700
Data Index: 4285540 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3476. Min Range: -6.3476
Max Act: 6.1913. Min Act: -0.1700
Data Index: 7443394 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3476. Min Range: -6.3476
Max Act: 6.1601. Min Act: -0.1700
Data Index: 6844283 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3476. Min Range: -6.3476
Max Act: 6.1601. Min Act: -0.1700
Data Index: 259298 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3476. Min Range: -6.3476
Max Act: 6.1601. Min Act: -0.1700
Data Index: 6447551 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3476. Min Range: -6.3476
Max Act: 6.1913. Min Act: -0.1700
Data Index: 7918703 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3476. Min Range: -6.3476
Max Act: 6.1601. Min Act: -0.1700
Data Index: 7449705 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3476. Min Range: -6.3476
Max Act: 6.1601. Min Act: -0.1700
Data Index: 2113337 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3476. Min Range: -6.3476
Max Act: 6.1288. Min Act: -0.1700
Data Index: 6615718 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3476. Min Range: -6.3476
Max Act: 6.1288. Min Act: -0.1700
Data Index: 697050 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3476. Min Range: -6.3476
Max Act: 6.0976. Min Act: -0.1700
Data Index: 6670901 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3476. Min Range: -6.3476
Max Act: 6.1288. Min Act: -0.1700
Data Index: 3089051 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #19