Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3556 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.0429. Min Range: -5.0429
Max Act: 5.0429. Min Act: -0.1700
Data Index: 1248805 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0429. Min Range: -5.0429
Max Act: 5.0116. Min Act: -0.1700
Data Index: 6601227 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0429. Min Range: -5.0429
Max Act: 5.0116. Min Act: -0.1700
Data Index: 554330 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0429. Min Range: -5.0429
Max Act: 5.0116. Min Act: -0.1700
Data Index: 2427315 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0429. Min Range: -5.0429
Max Act: 4.9804. Min Act: -0.1700
Data Index: 8335251 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0429. Min Range: -5.0429
Max Act: 4.9804. Min Act: -0.1700
Data Index: 2584509 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0429. Min Range: -5.0429
Max Act: 4.9804. Min Act: -0.1700
Data Index: 5971107 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0429. Min Range: -5.0429
Max Act: 4.9804. Min Act: -0.1700
Data Index: 4523629 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0429. Min Range: -5.0429
Max Act: 4.9804. Min Act: -0.1700
Data Index: 7754414 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0429. Min Range: -5.0429
Max Act: 4.9491. Min Act: -0.1700
Data Index: 2855034 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0429. Min Range: -5.0429
Max Act: 4.9491. Min Act: -0.1700
Data Index: 8505280 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0429. Min Range: -5.0429
Max Act: 4.9179. Min Act: -0.1700
Data Index: 3619024 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0429. Min Range: -5.0429
Max Act: 4.9179. Min Act: -0.1700
Data Index: 8364718 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0429. Min Range: -5.0429
Max Act: 4.9179. Min Act: -0.1700
Data Index: 1009328 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0429. Min Range: -5.0429
Max Act: 4.8866. Min Act: -0.1700
Data Index: 4927037 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0429. Min Range: -5.0429
Max Act: 4.9179. Min Act: -0.1700
Data Index: 7121650 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0429. Min Range: -5.0429
Max Act: 4.9179. Min Act: -0.1700
Data Index: 6047222 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0429. Min Range: -5.0429
Max Act: 4.9179. Min Act: -0.1700
Data Index: 16295 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0429. Min Range: -5.0429
Max Act: 4.8866. Min Act: -0.1700
Data Index: 6586215 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0429. Min Range: -5.0429
Max Act: 4.9179. Min Act: -0.1700
Data Index: 1704224 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #19