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

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

Neuron 3610 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4900. Min Range: -1.4900

Max Act: 1.4900. Min Act: -0.0000

Data Index: 1297361 (C4 (Web Text))

Max Activating Token Index: 729

Text #1

Max Range: 1.4900. Min Range: -1.4900

Max Act: 1.2286. Min Act: -0.0000

Data Index: 82098 (C4 (Web Text))

Max Activating Token Index: 117

Text #2

Max Range: 1.4900. Min Range: -1.4900

Max Act: 1.2265. Min Act: -0.0000

Data Index: 205150 (C4 (Web Text))

Max Activating Token Index: 108

Text #3

Max Range: 1.4900. Min Range: -1.4900

Max Act: 1.1690. Min Act: -0.0000

Data Index: 659682 (C4 (Web Text))

Max Activating Token Index: 248

Text #4

Max Range: 1.4900. Min Range: -1.4900

Max Act: 1.0669. Min Act: -0.0000

Data Index: 1312899 (C4 (Web Text))

Max Activating Token Index: 138

Text #5

Max Range: 1.4900. Min Range: -1.4900

Max Act: 1.1286. Min Act: -0.0000

Data Index: 765446 (C4 (Web Text))

Max Activating Token Index: 1003

Text #6

Max Range: 1.4900. Min Range: -1.4900

Max Act: 1.0930. Min Act: -0.0000

Data Index: 898237 (C4 (Web Text))

Max Activating Token Index: 453

Text #7

Max Range: 1.4900. Min Range: -1.4900

Max Act: 1.0228. Min Act: -0.0000

Data Index: 1243560 (C4 (Web Text))

Max Activating Token Index: 739

Text #8

Max Range: 1.4900. Min Range: -1.4900

Max Act: 0.9472. Min Act: -0.0000

Data Index: 1187393 (C4 (Web Text))

Max Activating Token Index: 1001

Text #9

Max Range: 1.4900. Min Range: -1.4900

Max Act: 1.0190. Min Act: -0.0000

Data Index: 624554 (C4 (Web Text))

Max Activating Token Index: 373

Text #10

Max Range: 1.4900. Min Range: -1.4900

Max Act: 1.0362. Min Act: -0.0000

Data Index: 509590 (C4 (Web Text))

Max Activating Token Index: 176

Text #11

Max Range: 1.4900. Min Range: -1.4900

Max Act: 0.9786. Min Act: -0.0000

Data Index: 459187 (C4 (Web Text))

Max Activating Token Index: 63

Text #12

Max Range: 1.4900. Min Range: -1.4900

Max Act: 0.9414. Min Act: -0.0000

Data Index: 962722 (C4 (Web Text))

Max Activating Token Index: 126

Text #13

Max Range: 1.4900. Min Range: -1.4900

Max Act: 0.9613. Min Act: -0.0000

Data Index: 694697 (C4 (Web Text))

Max Activating Token Index: 504

Text #14

Max Range: 1.4900. Min Range: -1.4900

Max Act: 0.9613. Min Act: -0.0000

Data Index: 642118 (C4 (Web Text))

Max Activating Token Index: 817

Text #15

Max Range: 1.4900. Min Range: -1.4900

Max Act: 0.9172. Min Act: -0.0000

Data Index: 893979 (C4 (Web Text))

Max Activating Token Index: 374

Text #16

Max Range: 1.4900. Min Range: -1.4900

Max Act: 0.9600. Min Act: -0.0000

Data Index: 1279493 (C4 (Web Text))

Max Activating Token Index: 416

Text #17

Max Range: 1.4900. Min Range: -1.4900

Max Act: 0.9563. Min Act: -0.0000

Data Index: 1224558 (C4 (Web Text))

Max Activating Token Index: 391

Text #18

Max Range: 1.4900. Min Range: -1.4900

Max Act: 0.8730. Min Act: -0.0000

Data Index: 510870 (C4 (Web Text))

Max Activating Token Index: 572

Text #19

Max Range: 1.4900. Min Range: -1.4900

Max Act: 0.8728. Min Act: -0.0000

Data Index: 821804 (C4 (Web Text))

Max Activating Token Index: 691