Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1838 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0537. Min Act: -0.0006

Data Index: 1257785 (C4 (Web Text))

Max Activating Token Index: 306

Text #1

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0503. Min Act: -0.0006

Data Index: 391018 (C4 (Web Text))

Max Activating Token Index: 999

Text #2

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0461. Min Act: -0.0006

Data Index: 473957 (C4 (Web Text))

Max Activating Token Index: 645

Text #3

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0468. Min Act: -0.0006

Data Index: 486979 (C4 (Web Text))

Max Activating Token Index: 283

Text #4

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0490. Min Act: -0.0006

Data Index: 421377 (C4 (Web Text))

Max Activating Token Index: 939

Text #5

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0457. Min Act: -0.0006

Data Index: 862321 (C4 (Web Text))

Max Activating Token Index: 464

Text #6

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0504. Min Act: -0.0006

Data Index: 591311 (C4 (Web Text))

Max Activating Token Index: 552

Text #7

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0493. Min Act: -0.0006

Data Index: 835353 (C4 (Web Text))

Max Activating Token Index: 752

Text #8

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0479. Min Act: -0.0006

Data Index: 778344 (C4 (Web Text))

Max Activating Token Index: 850

Text #9

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0484. Min Act: -0.0006

Data Index: 1302978 (C4 (Web Text))

Max Activating Token Index: 921

Text #10

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0470. Min Act: -0.0006

Data Index: 267176 (C4 (Web Text))

Max Activating Token Index: 909

Text #11

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0461. Min Act: -0.0006

Data Index: 798314 (C4 (Web Text))

Max Activating Token Index: 403

Text #12

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0482. Min Act: -0.0006

Data Index: 1358157 (C4 (Web Text))

Max Activating Token Index: 163

Text #13

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0469. Min Act: -0.0006

Data Index: 1052637 (C4 (Web Text))

Max Activating Token Index: 163

Text #14

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0447. Min Act: -0.0006

Data Index: 35880 (C4 (Web Text))

Max Activating Token Index: 789

Text #15

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0462. Min Act: -0.0006

Data Index: 257505 (C4 (Web Text))

Max Activating Token Index: 678

Text #16

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0485. Min Act: -0.0006

Data Index: 464692 (C4 (Web Text))

Max Activating Token Index: 931

Text #17

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0485. Min Act: -0.0006

Data Index: 223262 (C4 (Web Text))

Max Activating Token Index: 787

Text #18

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0434. Min Act: -0.0006

Data Index: 161332 (C4 (Web Text))

Max Activating Token Index: 921

Text #19

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0450. Min Act: -0.0006

Data Index: 480727 (C4 (Web Text))

Max Activating Token Index: 460