Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2152 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.1453. Min Range: -4.1453
Max Act: 4.1453. Min Act: -0.1700
Data Index: 8047036 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1453. Min Range: -4.1453
Max Act: 4.0203. Min Act: -0.1700
Data Index: 127705 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1453. Min Range: -4.1453
Max Act: 3.9891. Min Act: -0.1700
Data Index: 1824523 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1453. Min Range: -4.1453
Max Act: 3.9578. Min Act: -0.1700
Data Index: 3601661 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1453. Min Range: -4.1453
Max Act: 3.9891. Min Act: -0.1700
Data Index: 3824666 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1453. Min Range: -4.1453
Max Act: 3.9578. Min Act: -0.1700
Data Index: 1638749 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1453. Min Range: -4.1453
Max Act: 3.9578. Min Act: -0.1700
Data Index: 5319077 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1453. Min Range: -4.1453
Max Act: 3.9578. Min Act: -0.1700
Data Index: 8638174 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1453. Min Range: -4.1453
Max Act: 3.9578. Min Act: -0.1700
Data Index: 3332539 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1453. Min Range: -4.1453
Max Act: 3.8640. Min Act: -0.1700
Data Index: 4221570 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1453. Min Range: -4.1453
Max Act: 3.8484. Min Act: -0.1700
Data Index: 1719982 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1453. Min Range: -4.1453
Max Act: 3.8484. Min Act: -0.1700
Data Index: 163224 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1453. Min Range: -4.1453
Max Act: 3.8484. Min Act: -0.1700
Data Index: 228555 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1453. Min Range: -4.1453
Max Act: 3.8327. Min Act: -0.1700
Data Index: 22753 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1453. Min Range: -4.1453
Max Act: 3.8327. Min Act: -0.1700
Data Index: 5411680 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1453. Min Range: -4.1453
Max Act: 3.8171. Min Act: -0.1700
Data Index: 1315495 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1453. Min Range: -4.1453
Max Act: 3.8171. Min Act: -0.1700
Data Index: 6446800 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1453. Min Range: -4.1453
Max Act: 3.8327. Min Act: -0.1700
Data Index: 7607259 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1453. Min Range: -4.1453
Max Act: 3.8015. Min Act: -0.1700
Data Index: 1403418 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1453. Min Range: -4.1453
Max Act: 3.7858. Min Act: -0.1700
Data Index: 1371115 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #19