Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 2499 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 3.1563. Min Range: -3.1563
Max Act: 3.1563. Min Act: -0.1700
Data Index: 627672 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full textTruncated
Full Text #0
Text #1
Max Range: 3.1563. Min Range: -3.1563
Max Act: 3.1312. Min Act: -0.1700
Data Index: 4042250 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full textTruncated
Full Text #1
Text #2
Max Range: 3.1563. Min Range: -3.1563
Max Act: 3.1161. Min Act: -0.1700
Data Index: 3103668 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full textTruncated
Full Text #2
Text #3
Max Range: 3.1563. Min Range: -3.1563
Max Act: 3.0893. Min Act: -0.1700
Data Index: 1975967 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full textTruncated
Full Text #3
Text #4
Max Range: 3.1563. Min Range: -3.1563
Max Act: 3.0884. Min Act: -0.1700
Data Index: 5319236 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full textTruncated
Full Text #4
Text #5
Max Range: 3.1563. Min Range: -3.1563
Max Act: 3.0856. Min Act: -0.1700
Data Index: 3228231 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full textTruncated
Full Text #5
Text #6
Max Range: 3.1563. Min Range: -3.1563
Max Act: 3.0533. Min Act: -0.1700
Data Index: 1786850 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full textTruncated
Full Text #6
Text #7
Max Range: 3.1563. Min Range: -3.1563
Max Act: 3.0653. Min Act: -0.1700
Data Index: 706316 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full textTruncated
Full Text #7
Text #8
Max Range: 3.1563. Min Range: -3.1563
Max Act: 3.0366. Min Act: -0.1700
Data Index: 5618336 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full textTruncated
Full Text #8
Text #9
Max Range: 3.1563. Min Range: -3.1563
Max Act: 3.0396. Min Act: -0.1700
Data Index: 756737 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full textTruncated
Full Text #9
Text #10
Max Range: 3.1563. Min Range: -3.1563
Max Act: 3.0536. Min Act: -0.1700
Data Index: 6857797 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full textTruncated
Full Text #10
Text #11
Max Range: 3.1563. Min Range: -3.1563
Max Act: 3.0240. Min Act: -0.1700
Data Index: 7620087 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full textTruncated
Full Text #11
Text #12
Max Range: 3.1563. Min Range: -3.1563
Max Act: 3.0228. Min Act: -0.1700
Data Index: 3186716 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full textTruncated
Full Text #12
Text #13
Max Range: 3.1563. Min Range: -3.1563
Max Act: 3.0468. Min Act: -0.1700
Data Index: 5604588 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full textTruncated
Full Text #13
Text #14
Max Range: 3.1563. Min Range: -3.1563
Max Act: 3.0472. Min Act: -0.1700
Data Index: 2951310 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full textTruncated
Full Text #14
Text #15
Max Range: 3.1563. Min Range: -3.1563
Max Act: 3.0269. Min Act: -0.1700
Data Index: 4147073 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full textTruncated
Full Text #15
Text #16
Max Range: 3.1563. Min Range: -3.1563
Max Act: 3.0212. Min Act: -0.1700
Data Index: 4172689 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full textTruncated
Full Text #16
Text #17
Max Range: 3.1563. Min Range: -3.1563
Max Act: 3.0065. Min Act: -0.1700
Data Index: 6044340 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full textTruncated
Full Text #17
Text #18
Max Range: 3.1563. Min Range: -3.1563
Max Act: 3.0103. Min Act: -0.1700
Data Index: 3629530 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full textTruncated
Full Text #18
Text #19
Max Range: 3.1563. Min Range: -3.1563
Max Act: 3.0146. Min Act: -0.1700
Data Index: 4925987 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full textTruncated
Full Text #19