Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1689 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.5497. Min Range: -1.5497

Max Act: 1.5497. Min Act: -0.0000

Data Index: 336248 (C4 (Web Text))

Max Activating Token Index: 450

Text #1

Max Range: 1.5497. Min Range: -1.5497

Max Act: 1.3855. Min Act: -0.0000

Data Index: 772112 (C4 (Web Text))

Max Activating Token Index: 529

Text #2

Max Range: 1.5497. Min Range: -1.5497

Max Act: 1.2191. Min Act: -0.0000

Data Index: 1272544 (C4 (Web Text))

Max Activating Token Index: 36

Text #3

Max Range: 1.5497. Min Range: -1.5497

Max Act: 1.1707. Min Act: -0.0000

Data Index: 45134 (C4 (Web Text))

Max Activating Token Index: 184

Text #4

Max Range: 1.5497. Min Range: -1.5497

Max Act: 1.1030. Min Act: -0.0000

Data Index: 118222 (C4 (Web Text))

Max Activating Token Index: 859

Text #5

Max Range: 1.5497. Min Range: -1.5497

Max Act: 0.9671. Min Act: -0.0000

Data Index: 319319 (C4 (Web Text))

Max Activating Token Index: 345

Text #6

Max Range: 1.5497. Min Range: -1.5497

Max Act: 0.9813. Min Act: -0.0000

Data Index: 963483 (C4 (Web Text))

Max Activating Token Index: 43

Text #7

Max Range: 1.5497. Min Range: -1.5497

Max Act: 0.9497. Min Act: -0.0000

Data Index: 532360 (C4 (Web Text))

Max Activating Token Index: 554

Text #8

Max Range: 1.5497. Min Range: -1.5497

Max Act: 0.7979. Min Act: -0.0000

Data Index: 66529 (C4 (Web Text))

Max Activating Token Index: 271

Text #9

Max Range: 1.5497. Min Range: -1.5497

Max Act: 0.9594. Min Act: -0.0000

Data Index: 596173 (C4 (Web Text))

Max Activating Token Index: 32

Text #10

Max Range: 1.5497. Min Range: -1.5497

Max Act: 0.9296. Min Act: -0.0000

Data Index: 1197791 (C4 (Web Text))

Max Activating Token Index: 556

Text #11

Max Range: 1.5497. Min Range: -1.5497

Max Act: 0.9493. Min Act: -0.0000

Data Index: 828370 (C4 (Web Text))

Max Activating Token Index: 792

Text #12

Max Range: 1.5497. Min Range: -1.5497

Max Act: 0.8833. Min Act: -0.0000

Data Index: 162949 (C4 (Web Text))

Max Activating Token Index: 743

Text #13

Max Range: 1.5497. Min Range: -1.5497

Max Act: 0.9398. Min Act: -0.0000

Data Index: 562658 (C4 (Web Text))

Max Activating Token Index: 199

Text #14

Max Range: 1.5497. Min Range: -1.5497

Max Act: 0.9286. Min Act: -0.0000

Data Index: 74428 (C4 (Web Text))

Max Activating Token Index: 701

Text #15

Max Range: 1.5497. Min Range: -1.5497

Max Act: 0.9278. Min Act: -0.0000

Data Index: 1040857 (C4 (Web Text))

Max Activating Token Index: 703

Text #16

Max Range: 1.5497. Min Range: -1.5497

Max Act: 0.8938. Min Act: -0.0000

Data Index: 205457 (C4 (Web Text))

Max Activating Token Index: 1013

Text #17

Max Range: 1.5497. Min Range: -1.5497

Max Act: 0.8325. Min Act: -0.0000

Data Index: 381557 (C4 (Web Text))

Max Activating Token Index: 194

Text #18

Max Range: 1.5497. Min Range: -1.5497

Max Act: 1.0279. Min Act: -0.0000

Data Index: 467893 (C4 (Web Text))

Max Activating Token Index: 670

Text #19

Max Range: 1.5497. Min Range: -1.5497

Max Act: 0.8081. Min Act: -0.0000

Data Index: 1261491 (C4 (Web Text))

Max Activating Token Index: 264