Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1243 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.7538. Min Range: -8.7538
Max Act: 8.7538. Min Act: -0.1700
Data Index: 5066385 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7538. Min Range: -8.7538
Max Act: 8.6913. Min Act: -0.1700
Data Index: 5980548 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7538. Min Range: -8.7538
Max Act: 8.6913. Min Act: -0.1700
Data Index: 324510 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7538. Min Range: -8.7538
Max Act: 8.6913. Min Act: -0.1700
Data Index: 7790771 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7538. Min Range: -8.7538
Max Act: 8.6288. Min Act: -0.1700
Data Index: 7223855 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7538. Min Range: -8.7538
Max Act: 8.5663. Min Act: -0.1700
Data Index: 5135090 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7538. Min Range: -8.7538
Max Act: 8.5038. Min Act: -0.1700
Data Index: 6409701 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7538. Min Range: -8.7538
Max Act: 8.5038. Min Act: -0.1700
Data Index: 4505877 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7538. Min Range: -8.7538
Max Act: 8.5038. Min Act: -0.1700
Data Index: 2090598 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7538. Min Range: -8.7538
Max Act: 8.5038. Min Act: -0.1700
Data Index: 2676693 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7538. Min Range: -8.7538
Max Act: 8.5038. Min Act: -0.1700
Data Index: 5661428 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7538. Min Range: -8.7538
Max Act: 8.5038. Min Act: -0.1700
Data Index: 5083187 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7538. Min Range: -8.7538
Max Act: 8.5038. Min Act: -0.1700
Data Index: 1029603 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7538. Min Range: -8.7538
Max Act: 8.5038. Min Act: -0.1700
Data Index: 2713354 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7538. Min Range: -8.7538
Max Act: 8.5038. Min Act: -0.1700
Data Index: 2479295 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7538. Min Range: -8.7538
Max Act: 8.4413. Min Act: -0.1700
Data Index: 1963952 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7538. Min Range: -8.7538
Max Act: 8.4413. Min Act: -0.1700
Data Index: 6053284 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7538. Min Range: -8.7538
Max Act: 8.4413. Min Act: -0.1700
Data Index: 2174163 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7538. Min Range: -8.7538
Max Act: 8.4413. Min Act: -0.1700
Data Index: 4370687 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7538. Min Range: -8.7538
Max Act: 8.4413. Min Act: -0.1700
Data Index: 691941 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #19