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

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

Neuron 2352 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: 2.5703. Min Range: -2.5703

Max Act: 2.5492. Min Act: -0.0000

Data Index: 1327677 (C4 (Web Text))

Max Activating Token Index: 832

Text #1

Max Range: 2.5703. Min Range: -2.5703

Max Act: 2.5703. Min Act: -0.0000

Data Index: 792059 (C4 (Web Text))

Max Activating Token Index: 367

Text #2

Max Range: 2.5703. Min Range: -2.5703

Max Act: 2.4366. Min Act: -0.0000

Data Index: 1161858 (C4 (Web Text))

Max Activating Token Index: 24

Text #3

Max Range: 2.5703. Min Range: -2.5703

Max Act: 2.1247. Min Act: -0.0000

Data Index: 36529 (C4 (Web Text))

Max Activating Token Index: 62

Text #4

Max Range: 2.5703. Min Range: -2.5703

Max Act: 2.2124. Min Act: -0.0000

Data Index: 291943 (C4 (Web Text))

Max Activating Token Index: 195

Text #5

Max Range: 2.5703. Min Range: -2.5703

Max Act: 1.9707. Min Act: -0.0000

Data Index: 967059 (C4 (Web Text))

Max Activating Token Index: 181

Text #6

Max Range: 2.5703. Min Range: -2.5703

Max Act: 1.9624. Min Act: -0.0000

Data Index: 1146651 (C4 (Web Text))

Max Activating Token Index: 12

Text #7

Max Range: 2.5703. Min Range: -2.5703

Max Act: 1.9233. Min Act: -0.0000

Data Index: 668374 (C4 (Web Text))

Max Activating Token Index: 983

Text #8

Max Range: 2.5703. Min Range: -2.5703

Max Act: 1.8983. Min Act: -0.0000

Data Index: 546553 (C4 (Web Text))

Max Activating Token Index: 680

Text #9

Max Range: 2.5703. Min Range: -2.5703

Max Act: 2.0841. Min Act: -0.0000

Data Index: 1042962 (C4 (Web Text))

Max Activating Token Index: 42

Text #10

Max Range: 2.5703. Min Range: -2.5703

Max Act: 1.9532. Min Act: -0.0000

Data Index: 536805 (C4 (Web Text))

Max Activating Token Index: 721

Text #11

Max Range: 2.5703. Min Range: -2.5703

Max Act: 1.8248. Min Act: -0.0000

Data Index: 1359217 (C4 (Web Text))

Max Activating Token Index: 990

Text #12

Max Range: 2.5703. Min Range: -2.5703

Max Act: 1.9179. Min Act: -0.0000

Data Index: 434494 (C4 (Web Text))

Max Activating Token Index: 396

Text #13

Max Range: 2.5703. Min Range: -2.5703

Max Act: 1.9298. Min Act: -0.0000

Data Index: 1175409 (C4 (Web Text))

Max Activating Token Index: 391

Text #14

Max Range: 2.5703. Min Range: -2.5703

Max Act: 1.9996. Min Act: -0.0000

Data Index: 141420 (C4 (Web Text))

Max Activating Token Index: 162

Text #15

Max Range: 2.5703. Min Range: -2.5703

Max Act: 1.8841. Min Act: -0.0000

Data Index: 355998 (C4 (Web Text))

Max Activating Token Index: 852

Text #16

Max Range: 2.5703. Min Range: -2.5703

Max Act: 1.7838. Min Act: -0.0000

Data Index: 257495 (C4 (Web Text))

Max Activating Token Index: 204

Text #17

Max Range: 2.5703. Min Range: -2.5703

Max Act: 1.8393. Min Act: -0.0000

Data Index: 414115 (C4 (Web Text))

Max Activating Token Index: 330

Text #18

Max Range: 2.5703. Min Range: -2.5703

Max Act: 1.8303. Min Act: -0.0001

Data Index: 345454 (C4 (Web Text))

Max Activating Token Index: 950

Text #19

Max Range: 2.5703. Min Range: -2.5703

Max Act: 1.9381. Min Act: -0.0000

Data Index: 22662 (C4 (Web Text))

Max Activating Token Index: 9