Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3227 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.5171. Min Range: -5.5171
Max Act: 5.5171. Min Act: -0.1700
Data Index: 8364998 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5171. Min Range: -5.5171
Max Act: 5.3609. Min Act: -0.1700
Data Index: 1924109 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5171. Min Range: -5.5171
Max Act: 5.3609. Min Act: -0.1700
Data Index: 7140889 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5171. Min Range: -5.5171
Max Act: 5.3296. Min Act: -0.1700
Data Index: 758008 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5171. Min Range: -5.5171
Max Act: 5.2984. Min Act: -0.1700
Data Index: 3180412 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5171. Min Range: -5.5171
Max Act: 5.2359. Min Act: -0.1700
Data Index: 5263244 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5171. Min Range: -5.5171
Max Act: 5.2671. Min Act: -0.1700
Data Index: 1790823 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5171. Min Range: -5.5171
Max Act: 5.2046. Min Act: -0.1700
Data Index: 88539 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5171. Min Range: -5.5171
Max Act: 5.1421. Min Act: -0.1700
Data Index: 5996000 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5171. Min Range: -5.5171
Max Act: 5.1734. Min Act: -0.1700
Data Index: 4132264 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5171. Min Range: -5.5171
Max Act: 5.1734. Min Act: -0.1700
Data Index: 8817346 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5171. Min Range: -5.5171
Max Act: 5.1421. Min Act: -0.1700
Data Index: 5266311 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5171. Min Range: -5.5171
Max Act: 5.1421. Min Act: -0.1700
Data Index: 4032627 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5171. Min Range: -5.5171
Max Act: 5.1421. Min Act: -0.1700
Data Index: 7525871 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5171. Min Range: -5.5171
Max Act: 5.1421. Min Act: -0.1700
Data Index: 3878632 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5171. Min Range: -5.5171
Max Act: 5.1421. Min Act: -0.1700
Data Index: 2788432 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5171. Min Range: -5.5171
Max Act: 5.1109. Min Act: -0.1700
Data Index: 5165441 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5171. Min Range: -5.5171
Max Act: 5.1421. Min Act: -0.1700
Data Index: 841605 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5171. Min Range: -5.5171
Max Act: 5.1421. Min Act: -0.1700
Data Index: 6299986 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5171. Min Range: -5.5171
Max Act: 5.1421. Min Act: -0.1700
Data Index: 5874767 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #19