Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2595 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.0822. Min Range: -6.0822
Max Act: 6.0822. Min Act: -0.1700
Data Index: 793187 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0822. Min Range: -6.0822
Max Act: 6.0197. Min Act: -0.1700
Data Index: 5313556 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0822. Min Range: -6.0822
Max Act: 5.8635. Min Act: -0.1700
Data Index: 3477245 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0822. Min Range: -6.0822
Max Act: 5.8947. Min Act: -0.1700
Data Index: 7887209 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0822. Min Range: -6.0822
Max Act: 5.8010. Min Act: -0.1700
Data Index: 3034703 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0822. Min Range: -6.0822
Max Act: 5.7072. Min Act: -0.1700
Data Index: 2880154 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0822. Min Range: -6.0822
Max Act: 5.7385. Min Act: -0.1700
Data Index: 3499033 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0822. Min Range: -6.0822
Max Act: 5.7072. Min Act: -0.1700
Data Index: 1564495 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0822. Min Range: -6.0822
Max Act: 5.7072. Min Act: -0.1700
Data Index: 6997938 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0822. Min Range: -6.0822
Max Act: 5.7385. Min Act: -0.1700
Data Index: 6533530 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0822. Min Range: -6.0822
Max Act: 5.7385. Min Act: -0.1700
Data Index: 488975 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0822. Min Range: -6.0822
Max Act: 5.6447. Min Act: -0.1700
Data Index: 4437754 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0822. Min Range: -6.0822
Max Act: 5.6447. Min Act: -0.1700
Data Index: 7665484 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0822. Min Range: -6.0822
Max Act: 5.5510. Min Act: -0.1700
Data Index: 7142868 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0822. Min Range: -6.0822
Max Act: 5.5510. Min Act: -0.1700
Data Index: 7229758 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0822. Min Range: -6.0822
Max Act: 5.5510. Min Act: -0.1700
Data Index: 7546193 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0822. Min Range: -6.0822
Max Act: 5.5197. Min Act: -0.1700
Data Index: 5242394 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0822. Min Range: -6.0822
Max Act: 5.4885. Min Act: -0.1700
Data Index: 8294379 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0822. Min Range: -6.0822
Max Act: 5.5197. Min Act: -0.1700
Data Index: 6820524 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0822. Min Range: -6.0822
Max Act: 5.4885. Min Act: -0.1700
Data Index: 7591857 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #19