Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 585 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.3572. Min Range: -6.3572
Max Act: 6.3572. Min Act: -0.1700
Data Index: 800786 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3572. Min Range: -6.3572
Max Act: 6.2322. Min Act: -0.1700
Data Index: 5114469 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3572. Min Range: -6.3572
Max Act: 6.2009. Min Act: -0.1700
Data Index: 4075837 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3572. Min Range: -6.3572
Max Act: 6.1384. Min Act: -0.1700
Data Index: 8244045 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3572. Min Range: -6.3572
Max Act: 6.1072. Min Act: -0.1700
Data Index: 5370553 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3572. Min Range: -6.3572
Max Act: 6.1072. Min Act: -0.1700
Data Index: 2919363 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3572. Min Range: -6.3572
Max Act: 6.0134. Min Act: -0.1700
Data Index: 2602885 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3572. Min Range: -6.3572
Max Act: 5.9822. Min Act: -0.1700
Data Index: 368762 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3572. Min Range: -6.3572
Max Act: 5.9822. Min Act: -0.1700
Data Index: 8612504 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3572. Min Range: -6.3572
Max Act: 5.9509. Min Act: -0.1700
Data Index: 2763739 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3572. Min Range: -6.3572
Max Act: 5.9822. Min Act: -0.1700
Data Index: 2986046 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3572. Min Range: -6.3572
Max Act: 5.9197. Min Act: -0.1700
Data Index: 5766145 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3572. Min Range: -6.3572
Max Act: 5.8884. Min Act: -0.1700
Data Index: 7789323 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3572. Min Range: -6.3572
Max Act: 5.8884. Min Act: -0.1700
Data Index: 2783865 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3572. Min Range: -6.3572
Max Act: 5.9197. Min Act: -0.1700
Data Index: 8683744 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3572. Min Range: -6.3572
Max Act: 5.8884. Min Act: -0.1700
Data Index: 3673116 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3572. Min Range: -6.3572
Max Act: 5.8572. Min Act: -0.1700
Data Index: 2783864 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3572. Min Range: -6.3572
Max Act: 5.8884. Min Act: -0.1700
Data Index: 4899348 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3572. Min Range: -6.3572
Max Act: 5.9197. Min Act: -0.1700
Data Index: 3330966 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3572. Min Range: -6.3572
Max Act: 5.9197. Min Act: -0.1700
Data Index: 8495711 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19