Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1449 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0272. Min Range: -1.0272

Max Act: 1.0272. Min Act: -0.0001

Data Index: 999372 (C4 (Web Text))

Max Activating Token Index: 48

Text #1

Max Range: 1.0272. Min Range: -1.0272

Max Act: 1.0156. Min Act: -0.0000

Data Index: 195952 (C4 (Web Text))

Max Activating Token Index: 677

Text #2

Max Range: 1.0272. Min Range: -1.0272

Max Act: 0.9814. Min Act: -0.0000

Data Index: 1198656 (C4 (Web Text))

Max Activating Token Index: 339

Text #3

Max Range: 1.0272. Min Range: -1.0272

Max Act: 0.9352. Min Act: -0.0000

Data Index: 846081 (C4 (Web Text))

Max Activating Token Index: 250

Text #4

Max Range: 1.0272. Min Range: -1.0272

Max Act: 0.9881. Min Act: -0.0000

Data Index: 433811 (C4 (Web Text))

Max Activating Token Index: 84

Text #5

Max Range: 1.0272. Min Range: -1.0272

Max Act: 0.9253. Min Act: -0.0001

Data Index: 319342 (C4 (Web Text))

Max Activating Token Index: 205

Text #6

Max Range: 1.0272. Min Range: -1.0272

Max Act: 0.9115. Min Act: -0.0000

Data Index: 1225245 (C4 (Web Text))

Max Activating Token Index: 700

Text #7

Max Range: 1.0272. Min Range: -1.0272

Max Act: 0.8693. Min Act: -0.0001

Data Index: 1212393 (C4 (Web Text))

Max Activating Token Index: 875

Text #8

Max Range: 1.0272. Min Range: -1.0272

Max Act: 0.9239. Min Act: -0.0000

Data Index: 103477 (C4 (Web Text))

Max Activating Token Index: 715

Text #9

Max Range: 1.0272. Min Range: -1.0272

Max Act: 0.9195. Min Act: -0.0000

Data Index: 51476 (C4 (Web Text))

Max Activating Token Index: 249

Text #10

Max Range: 1.0272. Min Range: -1.0272

Max Act: 0.8506. Min Act: -0.0001

Data Index: 1112575 (C4 (Web Text))

Max Activating Token Index: 724

Text #11

Max Range: 1.0272. Min Range: -1.0272

Max Act: 0.8601. Min Act: -0.0000

Data Index: 347430 (C4 (Web Text))

Max Activating Token Index: 974

Text #12

Max Range: 1.0272. Min Range: -1.0272

Max Act: 0.8305. Min Act: -0.0000

Data Index: 1030637 (C4 (Web Text))

Max Activating Token Index: 513

Text #13

Max Range: 1.0272. Min Range: -1.0272

Max Act: 0.8270. Min Act: -0.0001

Data Index: 421014 (C4 (Web Text))

Max Activating Token Index: 534

Text #14

Max Range: 1.0272. Min Range: -1.0272

Max Act: 0.8735. Min Act: -0.0000

Data Index: 500095 (C4 (Web Text))

Max Activating Token Index: 513

Text #15

Max Range: 1.0272. Min Range: -1.0272

Max Act: 0.8715. Min Act: -0.0000

Data Index: 31978 (C4 (Web Text))

Max Activating Token Index: 957

Text #16

Max Range: 1.0272. Min Range: -1.0272

Max Act: 0.8303. Min Act: -0.0000

Data Index: 1046735 (C4 (Web Text))

Max Activating Token Index: 160

Text #17

Max Range: 1.0272. Min Range: -1.0272

Max Act: 0.8618. Min Act: -0.0000

Data Index: 898599 (C4 (Web Text))

Max Activating Token Index: 425

Text #18

Max Range: 1.0272. Min Range: -1.0272

Max Act: 0.7957. Min Act: -0.0000

Data Index: 159833 (C4 (Web Text))

Max Activating Token Index: 553

Text #19

Max Range: 1.0272. Min Range: -1.0272

Max Act: 0.8306. Min Act: -0.0000

Data Index: 1063795 (C4 (Web Text))

Max Activating Token Index: 250