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

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

Neuron 3241 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: 2.6409. Min Range: -2.6409

Max Act: 2.6409. Min Act: -0.0000

Data Index: 630606 (C4 (Web Text))

Max Activating Token Index: 746

Text #1

Max Range: 2.6409. Min Range: -2.6409

Max Act: 2.3949. Min Act: -0.0000

Data Index: 291682 (C4 (Web Text))

Max Activating Token Index: 181

Text #2

Max Range: 2.6409. Min Range: -2.6409

Max Act: 2.5019. Min Act: -0.0000

Data Index: 723083 (C4 (Web Text))

Max Activating Token Index: 65

Text #3

Max Range: 2.6409. Min Range: -2.6409

Max Act: 2.4332. Min Act: -0.0000

Data Index: 95494 (C4 (Web Text))

Max Activating Token Index: 108

Text #4

Max Range: 2.6409. Min Range: -2.6409

Max Act: 2.4294. Min Act: -0.0000

Data Index: 256643 (C4 (Web Text))

Max Activating Token Index: 719

Text #5

Max Range: 2.6409. Min Range: -2.6409

Max Act: 2.3686. Min Act: -0.0000

Data Index: 101283 (C4 (Web Text))

Max Activating Token Index: 145

Text #6

Max Range: 2.6409. Min Range: -2.6409

Max Act: 2.1149. Min Act: -0.0000

Data Index: 722070 (C4 (Web Text))

Max Activating Token Index: 807

Text #7

Max Range: 2.6409. Min Range: -2.6409

Max Act: 2.1228. Min Act: -0.0000

Data Index: 729834 (C4 (Web Text))

Max Activating Token Index: 645

Text #8

Max Range: 2.6409. Min Range: -2.6409

Max Act: 2.3256. Min Act: -0.0001

Data Index: 1026265 (C4 (Web Text))

Max Activating Token Index: 729

Text #9

Max Range: 2.6409. Min Range: -2.6409

Max Act: 2.2172. Min Act: -0.0000

Data Index: 723378 (C4 (Web Text))

Max Activating Token Index: 37

Text #10

Max Range: 2.6409. Min Range: -2.6409

Max Act: 2.2283. Min Act: -0.0000

Data Index: 1145074 (C4 (Web Text))

Max Activating Token Index: 988

Text #11

Max Range: 2.6409. Min Range: -2.6409

Max Act: 2.3777. Min Act: -0.0000

Data Index: 1315493 (C4 (Web Text))

Max Activating Token Index: 184

Text #12

Max Range: 2.6409. Min Range: -2.6409

Max Act: 2.2378. Min Act: -0.0000

Data Index: 267576 (C4 (Web Text))

Max Activating Token Index: 785

Text #13

Max Range: 2.6409. Min Range: -2.6409

Max Act: 2.1533. Min Act: -0.0000

Data Index: 657147 (C4 (Web Text))

Max Activating Token Index: 914

Text #14

Max Range: 2.6409. Min Range: -2.6409

Max Act: 2.2587. Min Act: -0.0000

Data Index: 120861 (C4 (Web Text))

Max Activating Token Index: 27

Text #15

Max Range: 2.6409. Min Range: -2.6409

Max Act: 2.2454. Min Act: -0.0000

Data Index: 8379 (C4 (Web Text))

Max Activating Token Index: 603

Text #16

Max Range: 2.6409. Min Range: -2.6409

Max Act: 2.2678. Min Act: -0.0000

Data Index: 1255180 (C4 (Web Text))

Max Activating Token Index: 479

Text #17

Max Range: 2.6409. Min Range: -2.6409

Max Act: 2.2189. Min Act: -0.0000

Data Index: 191218 (C4 (Web Text))

Max Activating Token Index: 166

Text #18

Max Range: 2.6409. Min Range: -2.6409

Max Act: 2.0925. Min Act: -0.0000

Data Index: 1114948 (C4 (Web Text))

Max Activating Token Index: 108

Text #19

Max Range: 2.6409. Min Range: -2.6409

Max Act: 2.1634. Min Act: -0.0000

Data Index: 1249309 (C4 (Web Text))

Max Activating Token Index: 844