Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 575 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.4671. Min Range: -6.4671
Max Act: 6.4671. Min Act: -0.1700
Data Index: 4752826 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4671. Min Range: -6.4671
Max Act: 6.2171. Min Act: -0.1700
Data Index: 400435 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4671. Min Range: -6.4671
Max Act: 6.1546. Min Act: -0.1700
Data Index: 4296146 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4671. Min Range: -6.4671
Max Act: 6.1858. Min Act: -0.1700
Data Index: 8805041 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4671. Min Range: -6.4671
Max Act: 6.1858. Min Act: -0.1700
Data Index: 2879138 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4671. Min Range: -6.4671
Max Act: 6.1858. Min Act: -0.1700
Data Index: 1293216 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4671. Min Range: -6.4671
Max Act: 6.1546. Min Act: -0.1700
Data Index: 6822714 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4671. Min Range: -6.4671
Max Act: 6.0608. Min Act: -0.1700
Data Index: 3815961 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4671. Min Range: -6.4671
Max Act: 6.0296. Min Act: -0.1700
Data Index: 4627534 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4671. Min Range: -6.4671
Max Act: 6.0296. Min Act: -0.1700
Data Index: 7862314 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4671. Min Range: -6.4671
Max Act: 6.0296. Min Act: -0.1700
Data Index: 3768729 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4671. Min Range: -6.4671
Max Act: 6.0296. Min Act: -0.1700
Data Index: 554482 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4671. Min Range: -6.4671
Max Act: 5.9983. Min Act: -0.1700
Data Index: 4482560 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4671. Min Range: -6.4671
Max Act: 5.9983. Min Act: -0.1700
Data Index: 1167838 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4671. Min Range: -6.4671
Max Act: 5.9983. Min Act: -0.1700
Data Index: 1362869 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4671. Min Range: -6.4671
Max Act: 5.9358. Min Act: -0.1700
Data Index: 3497667 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4671. Min Range: -6.4671
Max Act: 5.9046. Min Act: -0.1700
Data Index: 5427868 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4671. Min Range: -6.4671
Max Act: 5.8421. Min Act: -0.1700
Data Index: 7729026 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4671. Min Range: -6.4671
Max Act: 5.8733. Min Act: -0.1700
Data Index: 6011897 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4671. Min Range: -6.4671
Max Act: 5.8421. Min Act: -0.1700
Data Index: 4769146 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #19