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

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

Neuron 176 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1410. Min Range: -0.1410

Max Act: 0.1390. Min Act: -0.0000

Data Index: 559368 (C4 (Web Text))

Max Activating Token Index: 903

Text #1

Max Range: 0.1410. Min Range: -0.1410

Max Act: 0.1410. Min Act: -0.0000

Data Index: 658825 (C4 (Web Text))

Max Activating Token Index: 635

Text #2

Max Range: 0.1410. Min Range: -0.1410

Max Act: 0.1238. Min Act: -0.0001

Data Index: 1007415 (C4 (Web Text))

Max Activating Token Index: 480

Text #3

Max Range: 0.1410. Min Range: -0.1410

Max Act: 0.1286. Min Act: -0.0000

Data Index: 1286819 (C4 (Web Text))

Max Activating Token Index: 959

Text #4

Max Range: 0.1410. Min Range: -0.1410

Max Act: 0.1165. Min Act: -0.0000

Data Index: 1533515 (Python Code)

Max Activating Token Index: 74

Text #5

Max Range: 0.1410. Min Range: -0.1410

Max Act: 0.1085. Min Act: -0.0000

Data Index: 1111650 (C4 (Web Text))

Max Activating Token Index: 393

Text #6

Max Range: 0.1410. Min Range: -0.1410

Max Act: 0.1184. Min Act: -0.0000

Data Index: 438687 (C4 (Web Text))

Max Activating Token Index: 606

Text #7

Max Range: 0.1410. Min Range: -0.1410

Max Act: 0.1076. Min Act: -0.0000

Data Index: 1276413 (C4 (Web Text))

Max Activating Token Index: 255

Text #8

Max Range: 0.1410. Min Range: -0.1410

Max Act: 0.1139. Min Act: -0.0000

Data Index: 970230 (C4 (Web Text))

Max Activating Token Index: 752

Text #9

Max Range: 0.1410. Min Range: -0.1410

Max Act: 0.1034. Min Act: -0.0000

Data Index: 588568 (C4 (Web Text))

Max Activating Token Index: 560

Text #10

Max Range: 0.1410. Min Range: -0.1410

Max Act: 0.1053. Min Act: -0.0000

Data Index: 894016 (C4 (Web Text))

Max Activating Token Index: 56

Text #11

Max Range: 0.1410. Min Range: -0.1410

Max Act: 0.1010. Min Act: -0.0000

Data Index: 1154260 (C4 (Web Text))

Max Activating Token Index: 235

Text #12

Max Range: 0.1410. Min Range: -0.1410

Max Act: 0.0988. Min Act: -0.0001

Data Index: 576128 (C4 (Web Text))

Max Activating Token Index: 21

Text #13

Max Range: 0.1410. Min Range: -0.1410

Max Act: 0.1122. Min Act: -0.0000

Data Index: 1456157 (Python Code)

Max Activating Token Index: 861

Text #14

Max Range: 0.1410. Min Range: -0.1410

Max Act: 0.0944. Min Act: -0.0000

Data Index: 1513198 (Python Code)

Max Activating Token Index: 277

Text #15

Max Range: 0.1410. Min Range: -0.1410

Max Act: 0.0943. Min Act: -0.0000

Data Index: 722747 (C4 (Web Text))

Max Activating Token Index: 532

Text #16

Max Range: 0.1410. Min Range: -0.1410

Max Act: 0.0927. Min Act: -0.0000

Data Index: 1576175 (Python Code)

Max Activating Token Index: 719

Text #17

Max Range: 0.1410. Min Range: -0.1410

Max Act: 0.0949. Min Act: -0.0000

Data Index: 1016453 (C4 (Web Text))

Max Activating Token Index: 479

Text #18

Max Range: 0.1410. Min Range: -0.1410

Max Act: 0.0949. Min Act: -0.0000

Data Index: 56548 (C4 (Web Text))

Max Activating Token Index: 467

Text #19

Max Range: 0.1410. Min Range: -0.1410

Max Act: 0.0905. Min Act: -0.0001

Data Index: 1174254 (C4 (Web Text))

Max Activating Token Index: 241