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

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

Neuron 2402 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5942. Min Range: -0.5942

Max Act: 0.5942. Min Act: -0.0000

Data Index: 916026 (C4 (Web Text))

Max Activating Token Index: 552

Text #1

Max Range: 0.5942. Min Range: -0.5942

Max Act: 0.5182. Min Act: -0.0000

Data Index: 707019 (C4 (Web Text))

Max Activating Token Index: 553

Text #2

Max Range: 0.5942. Min Range: -0.5942

Max Act: 0.4629. Min Act: -0.0000

Data Index: 138843 (C4 (Web Text))

Max Activating Token Index: 346

Text #3

Max Range: 0.5942. Min Range: -0.5942

Max Act: 0.4838. Min Act: -0.0000

Data Index: 125673 (C4 (Web Text))

Max Activating Token Index: 698

Text #4

Max Range: 0.5942. Min Range: -0.5942

Max Act: 0.4304. Min Act: -0.0000

Data Index: 706259 (C4 (Web Text))

Max Activating Token Index: 997

Text #5

Max Range: 0.5942. Min Range: -0.5942

Max Act: 0.4636. Min Act: -0.0000

Data Index: 414642 (C4 (Web Text))

Max Activating Token Index: 644

Text #6

Max Range: 0.5942. Min Range: -0.5942

Max Act: 0.4477. Min Act: -0.0000

Data Index: 43257 (C4 (Web Text))

Max Activating Token Index: 449

Text #7

Max Range: 0.5942. Min Range: -0.5942

Max Act: 0.4316. Min Act: -0.0000

Data Index: 1013470 (C4 (Web Text))

Max Activating Token Index: 554

Text #8

Max Range: 0.5942. Min Range: -0.5942

Max Act: 0.4413. Min Act: -0.0000

Data Index: 19519 (C4 (Web Text))

Max Activating Token Index: 810

Text #9

Max Range: 0.5942. Min Range: -0.5942

Max Act: 0.4179. Min Act: -0.0000

Data Index: 96972 (C4 (Web Text))

Max Activating Token Index: 290

Text #10

Max Range: 0.5942. Min Range: -0.5942

Max Act: 0.4348. Min Act: -0.0000

Data Index: 620665 (C4 (Web Text))

Max Activating Token Index: 465

Text #11

Max Range: 0.5942. Min Range: -0.5942

Max Act: 0.4231. Min Act: -0.0000

Data Index: 235745 (C4 (Web Text))

Max Activating Token Index: 549

Text #12

Max Range: 0.5942. Min Range: -0.5942

Max Act: 0.4215. Min Act: -0.0000

Data Index: 73300 (C4 (Web Text))

Max Activating Token Index: 304

Text #13

Max Range: 0.5942. Min Range: -0.5942

Max Act: 0.4355. Min Act: -0.0000

Data Index: 748739 (C4 (Web Text))

Max Activating Token Index: 92

Text #14

Max Range: 0.5942. Min Range: -0.5942

Max Act: 0.4854. Min Act: -0.0000

Data Index: 783055 (C4 (Web Text))

Max Activating Token Index: 56

Text #15

Max Range: 0.5942. Min Range: -0.5942

Max Act: 0.4201. Min Act: -0.0000

Data Index: 855684 (C4 (Web Text))

Max Activating Token Index: 23

Text #16

Max Range: 0.5942. Min Range: -0.5942

Max Act: 0.4325. Min Act: -0.0000

Data Index: 417166 (C4 (Web Text))

Max Activating Token Index: 199

Text #17

Max Range: 0.5942. Min Range: -0.5942

Max Act: 0.3941. Min Act: -0.0000

Data Index: 330637 (C4 (Web Text))

Max Activating Token Index: 659

Text #18

Max Range: 0.5942. Min Range: -0.5942

Max Act: 0.3799. Min Act: -0.0000

Data Index: 773514 (C4 (Web Text))

Max Activating Token Index: 920

Text #19

Max Range: 0.5942. Min Range: -0.5942

Max Act: 0.3926. Min Act: -0.0000

Data Index: 1164954 (C4 (Web Text))

Max Activating Token Index: 156