Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3847 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.5671. Min Range: -6.5671
Max Act: 6.5671. Min Act: -0.1700
Data Index: 443373 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5671. Min Range: -6.5671
Max Act: 6.1609. Min Act: -0.1700
Data Index: 3996543 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5671. Min Range: -6.5671
Max Act: 6.1296. Min Act: -0.1700
Data Index: 5737303 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5671. Min Range: -6.5671
Max Act: 6.0671. Min Act: -0.1700
Data Index: 4115818 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5671. Min Range: -6.5671
Max Act: 6.0671. Min Act: -0.1700
Data Index: 5169191 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5671. Min Range: -6.5671
Max Act: 6.0671. Min Act: -0.1700
Data Index: 7660807 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5671. Min Range: -6.5671
Max Act: 6.0046. Min Act: -0.1700
Data Index: 1789730 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5671. Min Range: -6.5671
Max Act: 6.0046. Min Act: -0.1700
Data Index: 4552843 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5671. Min Range: -6.5671
Max Act: 5.9734. Min Act: -0.1700
Data Index: 7794601 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5671. Min Range: -6.5671
Max Act: 5.9421. Min Act: -0.1700
Data Index: 6041414 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5671. Min Range: -6.5671
Max Act: 5.8796. Min Act: -0.1700
Data Index: 3436849 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5671. Min Range: -6.5671
Max Act: 5.9109. Min Act: -0.1700
Data Index: 4864326 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5671. Min Range: -6.5671
Max Act: 5.8484. Min Act: -0.1700
Data Index: 3785560 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5671. Min Range: -6.5671
Max Act: 5.8484. Min Act: -0.1700
Data Index: 3575045 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5671. Min Range: -6.5671
Max Act: 5.8171. Min Act: -0.1700
Data Index: 7784120 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5671. Min Range: -6.5671
Max Act: 5.7546. Min Act: -0.1700
Data Index: 4587326 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5671. Min Range: -6.5671
Max Act: 5.7546. Min Act: -0.1700
Data Index: 5443003 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5671. Min Range: -6.5671
Max Act: 5.7234. Min Act: -0.1700
Data Index: 412493 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5671. Min Range: -6.5671
Max Act: 5.7234. Min Act: -0.1700
Data Index: 7263795 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5671. Min Range: -6.5671
Max Act: 5.7234. Min Act: -0.1700
Data Index: 2345250 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #19