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

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

Neuron 4423 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6941. Min Range: -0.6941

Max Act: 0.6941. Min Act: -0.0001

Data Index: 994292 (C4 (Web Text))

Max Activating Token Index: 686

Text #1

Max Range: 0.6941. Min Range: -0.6941

Max Act: 0.6263. Min Act: -0.0001

Data Index: 47591 (C4 (Web Text))

Max Activating Token Index: 647

Text #2

Max Range: 0.6941. Min Range: -0.6941

Max Act: 0.5207. Min Act: -0.0001

Data Index: 207530 (C4 (Web Text))

Max Activating Token Index: 607

Text #3

Max Range: 0.6941. Min Range: -0.6941

Max Act: 0.5394. Min Act: -0.0001

Data Index: 119051 (C4 (Web Text))

Max Activating Token Index: 837

Text #4

Max Range: 0.6941. Min Range: -0.6941

Max Act: 0.5389. Min Act: -0.0001

Data Index: 807416 (C4 (Web Text))

Max Activating Token Index: 562

Text #5

Max Range: 0.6941. Min Range: -0.6941

Max Act: 0.4918. Min Act: -0.0001

Data Index: 244184 (C4 (Web Text))

Max Activating Token Index: 86

Text #6

Max Range: 0.6941. Min Range: -0.6941

Max Act: 0.5030. Min Act: -0.0001

Data Index: 74527 (C4 (Web Text))

Max Activating Token Index: 636

Text #7

Max Range: 0.6941. Min Range: -0.6941

Max Act: 0.4784. Min Act: -0.0001

Data Index: 183641 (C4 (Web Text))

Max Activating Token Index: 337

Text #8

Max Range: 0.6941. Min Range: -0.6941

Max Act: 0.4741. Min Act: -0.0001

Data Index: 540280 (C4 (Web Text))

Max Activating Token Index: 435

Text #9

Max Range: 0.6941. Min Range: -0.6941

Max Act: 0.4848. Min Act: -0.0001

Data Index: 1049262 (C4 (Web Text))

Max Activating Token Index: 952

Text #10

Max Range: 0.6941. Min Range: -0.6941

Max Act: 0.4331. Min Act: -0.0001

Data Index: 294286 (C4 (Web Text))

Max Activating Token Index: 677

Text #11

Max Range: 0.6941. Min Range: -0.6941

Max Act: 0.4597. Min Act: -0.0001

Data Index: 1022399 (C4 (Web Text))

Max Activating Token Index: 258

Text #12

Max Range: 0.6941. Min Range: -0.6941

Max Act: 0.4453. Min Act: -0.0000

Data Index: 866074 (C4 (Web Text))

Max Activating Token Index: 564

Text #13

Max Range: 0.6941. Min Range: -0.6941

Max Act: 0.4351. Min Act: -0.0001

Data Index: 897967 (C4 (Web Text))

Max Activating Token Index: 172

Text #14

Max Range: 0.6941. Min Range: -0.6941

Max Act: 0.4257. Min Act: -0.0001

Data Index: 1102455 (C4 (Web Text))

Max Activating Token Index: 856

Text #15

Max Range: 0.6941. Min Range: -0.6941

Max Act: 0.4148. Min Act: -0.0001

Data Index: 1035005 (C4 (Web Text))

Max Activating Token Index: 742

Text #16

Max Range: 0.6941. Min Range: -0.6941

Max Act: 0.4378. Min Act: -0.0001

Data Index: 408504 (C4 (Web Text))

Max Activating Token Index: 870

Text #17

Max Range: 0.6941. Min Range: -0.6941

Max Act: 0.4192. Min Act: -0.0001

Data Index: 329402 (C4 (Web Text))

Max Activating Token Index: 490

Text #18

Max Range: 0.6941. Min Range: -0.6941

Max Act: 0.4316. Min Act: -0.0001

Data Index: 793216 (C4 (Web Text))

Max Activating Token Index: 76

Text #19

Max Range: 0.6941. Min Range: -0.6941

Max Act: 0.4192. Min Act: -0.0001

Data Index: 13772 (C4 (Web Text))

Max Activating Token Index: 133