Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4692 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.1937. Min Range: -1.1937

Max Act: 1.1937. Min Act: -0.0000

Data Index: 1207608 (C4 (Web Text))

Max Activating Token Index: 443

Text #1

Max Range: 1.1937. Min Range: -1.1937

Max Act: 1.1434. Min Act: -0.0000

Data Index: 982968 (C4 (Web Text))

Max Activating Token Index: 631

Text #2

Max Range: 1.1937. Min Range: -1.1937

Max Act: 1.1410. Min Act: -0.0000

Data Index: 1178942 (C4 (Web Text))

Max Activating Token Index: 170

Text #3

Max Range: 1.1937. Min Range: -1.1937

Max Act: 1.0895. Min Act: -0.0000

Data Index: 1121539 (C4 (Web Text))

Max Activating Token Index: 132

Text #4

Max Range: 1.1937. Min Range: -1.1937

Max Act: 1.0609. Min Act: -0.0000

Data Index: 516557 (C4 (Web Text))

Max Activating Token Index: 429

Text #5

Max Range: 1.1937. Min Range: -1.1937

Max Act: 1.0491. Min Act: -0.0000

Data Index: 699172 (C4 (Web Text))

Max Activating Token Index: 16

Text #6

Max Range: 1.1937. Min Range: -1.1937

Max Act: 1.0472. Min Act: -0.0000

Data Index: 1183126 (C4 (Web Text))

Max Activating Token Index: 888

Text #7

Max Range: 1.1937. Min Range: -1.1937

Max Act: 1.0656. Min Act: -0.0000

Data Index: 601947 (C4 (Web Text))

Max Activating Token Index: 134

Text #8

Max Range: 1.1937. Min Range: -1.1937

Max Act: 1.0702. Min Act: -0.0000

Data Index: 143336 (C4 (Web Text))

Max Activating Token Index: 280

Text #9

Max Range: 1.1937. Min Range: -1.1937

Max Act: 1.0360. Min Act: -0.0000

Data Index: 57859 (C4 (Web Text))

Max Activating Token Index: 677

Text #10

Max Range: 1.1937. Min Range: -1.1937

Max Act: 1.0414. Min Act: -0.0000

Data Index: 837183 (C4 (Web Text))

Max Activating Token Index: 103

Text #11

Max Range: 1.1937. Min Range: -1.1937

Max Act: 1.0212. Min Act: -0.0000

Data Index: 711176 (C4 (Web Text))

Max Activating Token Index: 204

Text #12

Max Range: 1.1937. Min Range: -1.1937

Max Act: 1.0271. Min Act: -0.0000

Data Index: 1027255 (C4 (Web Text))

Max Activating Token Index: 53

Text #13

Max Range: 1.1937. Min Range: -1.1937

Max Act: 1.0249. Min Act: -0.0000

Data Index: 150967 (C4 (Web Text))

Max Activating Token Index: 267

Text #14

Max Range: 1.1937. Min Range: -1.1937

Max Act: 1.0245. Min Act: -0.0000

Data Index: 789494 (C4 (Web Text))

Max Activating Token Index: 336

Text #15

Max Range: 1.1937. Min Range: -1.1937

Max Act: 1.0141. Min Act: -0.0000

Data Index: 182249 (C4 (Web Text))

Max Activating Token Index: 795

Text #16

Max Range: 1.1937. Min Range: -1.1937

Max Act: 1.0433. Min Act: -0.0000

Data Index: 1312671 (C4 (Web Text))

Max Activating Token Index: 111

Text #17

Max Range: 1.1937. Min Range: -1.1937

Max Act: 1.0171. Min Act: -0.0000

Data Index: 1183833 (C4 (Web Text))

Max Activating Token Index: 171

Text #18

Max Range: 1.1937. Min Range: -1.1937

Max Act: 1.0111. Min Act: -0.0000

Data Index: 1265579 (C4 (Web Text))

Max Activating Token Index: 990

Text #19

Max Range: 1.1937. Min Range: -1.1937

Max Act: 1.0111. Min Act: -0.0000

Data Index: 592814 (C4 (Web Text))

Max Activating Token Index: 464