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

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

Neuron 3166 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: 0.5942. Min Range: -0.5942

Max Act: 0.5942. Min Act: -0.0000

Data Index: 1059572 (C4 (Web Text))

Max Activating Token Index: 285

Text #1

Max Range: 0.5942. Min Range: -0.5942

Max Act: 0.4705. Min Act: -0.0000

Data Index: 814348 (C4 (Web Text))

Max Activating Token Index: 739

Text #2

Max Range: 0.5942. Min Range: -0.5942

Max Act: 0.4820. Min Act: -0.0000

Data Index: 1195812 (C4 (Web Text))

Max Activating Token Index: 721

Text #3

Max Range: 0.5942. Min Range: -0.5942

Max Act: 0.4604. Min Act: -0.0000

Data Index: 68461 (C4 (Web Text))

Max Activating Token Index: 283

Text #4

Max Range: 0.5942. Min Range: -0.5942

Max Act: 0.4434. Min Act: -0.0000

Data Index: 282710 (C4 (Web Text))

Max Activating Token Index: 846

Text #5

Max Range: 0.5942. Min Range: -0.5942

Max Act: 0.4376. Min Act: -0.0000

Data Index: 1013082 (C4 (Web Text))

Max Activating Token Index: 514

Text #6

Max Range: 0.5942. Min Range: -0.5942

Max Act: 0.4804. Min Act: -0.0000

Data Index: 480954 (C4 (Web Text))

Max Activating Token Index: 994

Text #7

Max Range: 0.5942. Min Range: -0.5942

Max Act: 0.4595. Min Act: 0.0000

Data Index: 270571 (C4 (Web Text))

Max Activating Token Index: 919

Text #8

Max Range: 0.5942. Min Range: -0.5942

Max Act: 0.4239. Min Act: -0.0000

Data Index: 835653 (C4 (Web Text))

Max Activating Token Index: 131

Text #9

Max Range: 0.5942. Min Range: -0.5942

Max Act: 0.4693. Min Act: -0.0000

Data Index: 657929 (C4 (Web Text))

Max Activating Token Index: 821

Text #10

Max Range: 0.5942. Min Range: -0.5942

Max Act: 0.4220. Min Act: -0.0000

Data Index: 1220301 (C4 (Web Text))

Max Activating Token Index: 782

Text #11

Max Range: 0.5942. Min Range: -0.5942

Max Act: 0.4367. Min Act: -0.0000

Data Index: 805362 (C4 (Web Text))

Max Activating Token Index: 380

Text #12

Max Range: 0.5942. Min Range: -0.5942

Max Act: 0.4367. Min Act: -0.0000

Data Index: 358477 (C4 (Web Text))

Max Activating Token Index: 805

Text #13

Max Range: 0.5942. Min Range: -0.5942

Max Act: 0.4279. Min Act: -0.0000

Data Index: 157825 (C4 (Web Text))

Max Activating Token Index: 474

Text #14

Max Range: 0.5942. Min Range: -0.5942

Max Act: 0.4269. Min Act: -0.0000

Data Index: 309429 (C4 (Web Text))

Max Activating Token Index: 915

Text #15

Max Range: 0.5942. Min Range: -0.5942

Max Act: 0.4110. Min Act: -0.0000

Data Index: 195170 (C4 (Web Text))

Max Activating Token Index: 347

Text #16

Max Range: 0.5942. Min Range: -0.5942

Max Act: 0.4480. Min Act: -0.0000

Data Index: 391030 (C4 (Web Text))

Max Activating Token Index: 243

Text #17

Max Range: 0.5942. Min Range: -0.5942

Max Act: 0.4130. Min Act: -0.0000

Data Index: 1326823 (C4 (Web Text))

Max Activating Token Index: 745

Text #18

Max Range: 0.5942. Min Range: -0.5942

Max Act: 0.4131. Min Act: -0.0000

Data Index: 594014 (C4 (Web Text))

Max Activating Token Index: 481

Text #19

Max Range: 0.5942. Min Range: -0.5942

Max Act: 0.4098. Min Act: -0.0000

Data Index: 276078 (C4 (Web Text))

Max Activating Token Index: 923