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

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

Neuron 423 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5328. Min Range: -3.5328

Max Act: 3.5328. Min Act: -0.0000

Data Index: 354793 (C4 (Web Text))

Max Activating Token Index: 13

Text #1

Max Range: 3.5328. Min Range: -3.5328

Max Act: 3.2845. Min Act: -0.0000

Data Index: 1276160 (C4 (Web Text))

Max Activating Token Index: 599

Text #2

Max Range: 3.5328. Min Range: -3.5328

Max Act: 3.4360. Min Act: -0.0000

Data Index: 456059 (C4 (Web Text))

Max Activating Token Index: 375

Text #3

Max Range: 3.5328. Min Range: -3.5328

Max Act: 3.2462. Min Act: -0.0000

Data Index: 1029357 (C4 (Web Text))

Max Activating Token Index: 59

Text #4

Max Range: 3.5328. Min Range: -3.5328

Max Act: 3.0006. Min Act: -0.0000

Data Index: 501679 (C4 (Web Text))

Max Activating Token Index: 450

Text #5

Max Range: 3.5328. Min Range: -3.5328

Max Act: 3.2834. Min Act: -0.0000

Data Index: 1209299 (C4 (Web Text))

Max Activating Token Index: 119

Text #6

Max Range: 3.5328. Min Range: -3.5328

Max Act: 2.8383. Min Act: -0.0000

Data Index: 1350046 (C4 (Web Text))

Max Activating Token Index: 442

Text #7

Max Range: 3.5328. Min Range: -3.5328

Max Act: 3.1063. Min Act: -0.0000

Data Index: 384369 (C4 (Web Text))

Max Activating Token Index: 141

Text #8

Max Range: 3.5328. Min Range: -3.5328

Max Act: 3.2301. Min Act: -0.0000

Data Index: 204535 (C4 (Web Text))

Max Activating Token Index: 923

Text #9

Max Range: 3.5328. Min Range: -3.5328

Max Act: 2.6362. Min Act: -0.0000

Data Index: 879866 (C4 (Web Text))

Max Activating Token Index: 97

Text #10

Max Range: 3.5328. Min Range: -3.5328

Max Act: 2.9015. Min Act: -0.0000

Data Index: 666339 (C4 (Web Text))

Max Activating Token Index: 149

Text #11

Max Range: 3.5328. Min Range: -3.5328

Max Act: 2.4527. Min Act: -0.0000

Data Index: 1345549 (C4 (Web Text))

Max Activating Token Index: 480

Text #12

Max Range: 3.5328. Min Range: -3.5328

Max Act: 2.4415. Min Act: -0.0000

Data Index: 196555 (C4 (Web Text))

Max Activating Token Index: 830

Text #13

Max Range: 3.5328. Min Range: -3.5328

Max Act: 2.7145. Min Act: -0.0000

Data Index: 253049 (C4 (Web Text))

Max Activating Token Index: 105

Text #14

Max Range: 3.5328. Min Range: -3.5328

Max Act: 2.6760. Min Act: -0.0000

Data Index: 459300 (C4 (Web Text))

Max Activating Token Index: 325

Text #15

Max Range: 3.5328. Min Range: -3.5328

Max Act: 2.8238. Min Act: -0.0000

Data Index: 52434 (C4 (Web Text))

Max Activating Token Index: 985

Text #16

Max Range: 3.5328. Min Range: -3.5328

Max Act: 2.8984. Min Act: -0.0000

Data Index: 484008 (C4 (Web Text))

Max Activating Token Index: 219

Text #17

Max Range: 3.5328. Min Range: -3.5328

Max Act: 2.5999. Min Act: -0.0000

Data Index: 908024 (C4 (Web Text))

Max Activating Token Index: 205

Text #18

Max Range: 3.5328. Min Range: -3.5328

Max Act: 2.5964. Min Act: -0.0000

Data Index: 318154 (C4 (Web Text))

Max Activating Token Index: 515

Text #19

Max Range: 3.5328. Min Range: -3.5328

Max Act: 2.4680. Min Act: -0.0000

Data Index: 157116 (C4 (Web Text))

Max Activating Token Index: 215