Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2417 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.1733. Min Range: -7.1733
Max Act: 7.1733. Min Act: -0.1700
Data Index: 1943513 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1733. Min Range: -7.1733
Max Act: 7.0171. Min Act: -0.1700
Data Index: 7682555 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1733. Min Range: -7.1733
Max Act: 7.0171. Min Act: -0.1700
Data Index: 5930653 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1733. Min Range: -7.1733
Max Act: 7.0171. Min Act: -0.1700
Data Index: 534523 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1733. Min Range: -7.1733
Max Act: 6.9858. Min Act: -0.1700
Data Index: 8074626 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1733. Min Range: -7.1733
Max Act: 6.9233. Min Act: -0.1700
Data Index: 6689532 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1733. Min Range: -7.1733
Max Act: 6.8921. Min Act: -0.1700
Data Index: 1647259 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1733. Min Range: -7.1733
Max Act: 6.9233. Min Act: -0.1700
Data Index: 6096173 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1733. Min Range: -7.1733
Max Act: 6.8921. Min Act: -0.1700
Data Index: 1279220 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1733. Min Range: -7.1733
Max Act: 6.8608. Min Act: -0.1700
Data Index: 7985560 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1733. Min Range: -7.1733
Max Act: 6.8608. Min Act: -0.1700
Data Index: 534524 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1733. Min Range: -7.1733
Max Act: 6.8296. Min Act: -0.1700
Data Index: 3825128 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1733. Min Range: -7.1733
Max Act: 6.8296. Min Act: -0.1700
Data Index: 1620335 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1733. Min Range: -7.1733
Max Act: 6.8296. Min Act: -0.1700
Data Index: 6132185 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1733. Min Range: -7.1733
Max Act: 6.8296. Min Act: -0.1700
Data Index: 6619353 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1733. Min Range: -7.1733
Max Act: 6.7983. Min Act: -0.1700
Data Index: 766655 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1733. Min Range: -7.1733
Max Act: 6.8296. Min Act: -0.1700
Data Index: 6293220 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1733. Min Range: -7.1733
Max Act: 6.7983. Min Act: -0.1700
Data Index: 2919764 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1733. Min Range: -7.1733
Max Act: 6.7671. Min Act: -0.1700
Data Index: 7082729 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1733. Min Range: -7.1733
Max Act: 6.7671. Min Act: -0.1700
Data Index: 7546410 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #19