Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2231 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.5279. Min Range: -0.5279

Max Act: 0.4722. Min Act: -0.0001

Data Index: 84254 (C4 (Web Text))

Max Activating Token Index: 569

Text #1

Max Range: 0.5279. Min Range: -0.5279

Max Act: 0.4864. Min Act: -0.0001

Data Index: 367739 (C4 (Web Text))

Max Activating Token Index: 543

Text #2

Max Range: 0.5279. Min Range: -0.5279

Max Act: 0.4937. Min Act: -0.0001

Data Index: 288218 (C4 (Web Text))

Max Activating Token Index: 347

Text #3

Max Range: 0.5279. Min Range: -0.5279

Max Act: 0.5279. Min Act: -0.0001

Data Index: 432277 (C4 (Web Text))

Max Activating Token Index: 755

Text #4

Max Range: 0.5279. Min Range: -0.5279

Max Act: 0.4959. Min Act: -0.0001

Data Index: 436594 (C4 (Web Text))

Max Activating Token Index: 83

Text #5

Max Range: 0.5279. Min Range: -0.5279

Max Act: 0.4822. Min Act: -0.0001

Data Index: 40079 (C4 (Web Text))

Max Activating Token Index: 30

Text #6

Max Range: 0.5279. Min Range: -0.5279

Max Act: 0.4600. Min Act: -0.0001

Data Index: 808126 (C4 (Web Text))

Max Activating Token Index: 1019

Text #7

Max Range: 0.5279. Min Range: -0.5279

Max Act: 0.4690. Min Act: -0.0001

Data Index: 435791 (C4 (Web Text))

Max Activating Token Index: 660

Text #8

Max Range: 0.5279. Min Range: -0.5279

Max Act: 0.4460. Min Act: -0.0001

Data Index: 1220778 (C4 (Web Text))

Max Activating Token Index: 190

Text #9

Max Range: 0.5279. Min Range: -0.5279

Max Act: 0.5210. Min Act: -0.0001

Data Index: 721377 (C4 (Web Text))

Max Activating Token Index: 926

Text #10

Max Range: 0.5279. Min Range: -0.5279

Max Act: 0.4721. Min Act: -0.0001

Data Index: 192084 (C4 (Web Text))

Max Activating Token Index: 367

Text #11

Max Range: 0.5279. Min Range: -0.5279

Max Act: 0.4376. Min Act: -0.0001

Data Index: 1277890 (C4 (Web Text))

Max Activating Token Index: 614

Text #12

Max Range: 0.5279. Min Range: -0.5279

Max Act: 0.4207. Min Act: -0.0001

Data Index: 972016 (C4 (Web Text))

Max Activating Token Index: 320

Text #13

Max Range: 0.5279. Min Range: -0.5279

Max Act: 0.4355. Min Act: -0.0001

Data Index: 426332 (C4 (Web Text))

Max Activating Token Index: 943

Text #14

Max Range: 0.5279. Min Range: -0.5279

Max Act: 0.3931. Min Act: -0.0001

Data Index: 655912 (C4 (Web Text))

Max Activating Token Index: 204

Text #15

Max Range: 0.5279. Min Range: -0.5279

Max Act: 0.3943. Min Act: -0.0001

Data Index: 1076549 (C4 (Web Text))

Max Activating Token Index: 273

Text #16

Max Range: 0.5279. Min Range: -0.5279

Max Act: 0.4320. Min Act: -0.0001

Data Index: 715111 (C4 (Web Text))

Max Activating Token Index: 374

Text #17

Max Range: 0.5279. Min Range: -0.5279

Max Act: 0.4283. Min Act: -0.0001

Data Index: 372800 (C4 (Web Text))

Max Activating Token Index: 381

Text #18

Max Range: 0.5279. Min Range: -0.5279

Max Act: 0.4616. Min Act: -0.0001

Data Index: 386827 (C4 (Web Text))

Max Activating Token Index: 791

Text #19

Max Range: 0.5279. Min Range: -0.5279

Max Act: 0.3850. Min Act: -0.0001

Data Index: 1332535 (C4 (Web Text))

Max Activating Token Index: 173