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

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

Neuron 4675 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: 4.6385. Min Range: -4.6385

Max Act: 4.4244. Min Act: -0.0000

Data Index: 763511 (C4 (Web Text))

Max Activating Token Index: 949

Text #1

Max Range: 4.6385. Min Range: -4.6385

Max Act: 4.6153. Min Act: -0.0000

Data Index: 678146 (C4 (Web Text))

Max Activating Token Index: 257

Text #2

Max Range: 4.6385. Min Range: -4.6385

Max Act: 4.5793. Min Act: -0.0000

Data Index: 43016 (C4 (Web Text))

Max Activating Token Index: 975

Text #3

Max Range: 4.6385. Min Range: -4.6385

Max Act: 4.6073. Min Act: -0.0000

Data Index: 813890 (C4 (Web Text))

Max Activating Token Index: 992

Text #4

Max Range: 4.6385. Min Range: -4.6385

Max Act: 4.4401. Min Act: -0.0000

Data Index: 280648 (C4 (Web Text))

Max Activating Token Index: 1020

Text #5

Max Range: 4.6385. Min Range: -4.6385

Max Act: 4.4947. Min Act: -0.0000

Data Index: 1288816 (C4 (Web Text))

Max Activating Token Index: 1022

Text #6

Max Range: 4.6385. Min Range: -4.6385

Max Act: 4.6385. Min Act: -0.0000

Data Index: 549873 (C4 (Web Text))

Max Activating Token Index: 138

Text #7

Max Range: 4.6385. Min Range: -4.6385

Max Act: 4.4677. Min Act: -0.0000

Data Index: 641764 (C4 (Web Text))

Max Activating Token Index: 889

Text #8

Max Range: 4.6385. Min Range: -4.6385

Max Act: 4.2165. Min Act: -0.0000

Data Index: 1206949 (C4 (Web Text))

Max Activating Token Index: 991

Text #9

Max Range: 4.6385. Min Range: -4.6385

Max Act: 4.3479. Min Act: -0.0000

Data Index: 454127 (C4 (Web Text))

Max Activating Token Index: 659

Text #10

Max Range: 4.6385. Min Range: -4.6385

Max Act: 3.8505. Min Act: -0.0000

Data Index: 680264 (C4 (Web Text))

Max Activating Token Index: 792

Text #11

Max Range: 4.6385. Min Range: -4.6385

Max Act: 3.9703. Min Act: -0.0000

Data Index: 806509 (C4 (Web Text))

Max Activating Token Index: 1018

Text #12

Max Range: 4.6385. Min Range: -4.6385

Max Act: 4.1498. Min Act: -0.0000

Data Index: 249222 (C4 (Web Text))

Max Activating Token Index: 409

Text #13

Max Range: 4.6385. Min Range: -4.6385

Max Act: 4.4559. Min Act: -0.0000

Data Index: 1217552 (C4 (Web Text))

Max Activating Token Index: 964

Text #14

Max Range: 4.6385. Min Range: -4.6385

Max Act: 3.8858. Min Act: -0.0000

Data Index: 940939 (C4 (Web Text))

Max Activating Token Index: 17

Text #15

Max Range: 4.6385. Min Range: -4.6385

Max Act: 3.9881. Min Act: -0.0000

Data Index: 671984 (C4 (Web Text))

Max Activating Token Index: 870

Text #16

Max Range: 4.6385. Min Range: -4.6385

Max Act: 4.3138. Min Act: -0.0000

Data Index: 260539 (C4 (Web Text))

Max Activating Token Index: 539

Text #17

Max Range: 4.6385. Min Range: -4.6385

Max Act: 3.6305. Min Act: -0.0000

Data Index: 1344969 (C4 (Web Text))

Max Activating Token Index: 969

Text #18

Max Range: 4.6385. Min Range: -4.6385

Max Act: 3.7712. Min Act: -0.0000

Data Index: 402167 (C4 (Web Text))

Max Activating Token Index: 990

Text #19

Max Range: 4.6385. Min Range: -4.6385

Max Act: 3.8929. Min Act: -0.0000

Data Index: 853121 (C4 (Web Text))

Max Activating Token Index: 339