Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2526 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.0516. Min Range: -4.0516
Max Act: 4.0516. Min Act: -0.1699
Data Index: 8195776 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0516. Min Range: -4.0516
Max Act: 3.9579. Min Act: -0.1700
Data Index: 3057409 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0516. Min Range: -4.0516
Max Act: 3.9579. Min Act: -0.1699
Data Index: 3946676 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0516. Min Range: -4.0516
Max Act: 3.9266. Min Act: -0.1700
Data Index: 3164617 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0516. Min Range: -4.0516
Max Act: 3.9266. Min Act: -0.1699
Data Index: 8245522 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0516. Min Range: -4.0516
Max Act: 3.9266. Min Act: -0.1700
Data Index: 8175176 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0516. Min Range: -4.0516
Max Act: 3.9266. Min Act: -0.1700
Data Index: 7681247 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0516. Min Range: -4.0516
Max Act: 3.8953. Min Act: -0.1700
Data Index: 2805537 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0516. Min Range: -4.0516
Max Act: 3.8953. Min Act: -0.1700
Data Index: 49925 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0516. Min Range: -4.0516
Max Act: 3.8953. Min Act: -0.1700
Data Index: 2750586 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0516. Min Range: -4.0516
Max Act: 3.8953. Min Act: -0.1700
Data Index: 7276018 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0516. Min Range: -4.0516
Max Act: 3.8953. Min Act: -0.1700
Data Index: 6872367 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0516. Min Range: -4.0516
Max Act: 3.8953. Min Act: -0.1700
Data Index: 2459468 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0516. Min Range: -4.0516
Max Act: 3.9266. Min Act: -0.1700
Data Index: 6742554 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0516. Min Range: -4.0516
Max Act: 3.8953. Min Act: -0.1700
Data Index: 715452 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0516. Min Range: -4.0516
Max Act: 3.8953. Min Act: -0.1700
Data Index: 5313898 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0516. Min Range: -4.0516
Max Act: 3.8953. Min Act: -0.1700
Data Index: 4044121 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0516. Min Range: -4.0516
Max Act: 3.9266. Min Act: -0.1700
Data Index: 679864 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0516. Min Range: -4.0516
Max Act: 3.8953. Min Act: -0.1700
Data Index: 1390644 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0516. Min Range: -4.0516
Max Act: 3.8953. Min Act: -0.1700
Data Index: 1312690 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #19