Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 396 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0409. Min Range: -0.0409

Max Act: 0.0409. Min Act: -0.0006

Data Index: 1300783 (C4 (Web Text))

Max Activating Token Index: 33

Text #1

Max Range: 0.0409. Min Range: -0.0409

Max Act: 0.0400. Min Act: -0.0006

Data Index: 1347719 (C4 (Web Text))

Max Activating Token Index: 332

Text #2

Max Range: 0.0409. Min Range: -0.0409

Max Act: 0.0388. Min Act: -0.0006

Data Index: 922570 (C4 (Web Text))

Max Activating Token Index: 433

Text #3

Max Range: 0.0409. Min Range: -0.0409

Max Act: 0.0382. Min Act: -0.0006

Data Index: 1138460 (C4 (Web Text))

Max Activating Token Index: 870

Text #4

Max Range: 0.0409. Min Range: -0.0409

Max Act: 0.0371. Min Act: -0.0006

Data Index: 772227 (C4 (Web Text))

Max Activating Token Index: 633

Text #5

Max Range: 0.0409. Min Range: -0.0409

Max Act: 0.0361. Min Act: -0.0006

Data Index: 1169325 (C4 (Web Text))

Max Activating Token Index: 355

Text #6

Max Range: 0.0409. Min Range: -0.0409

Max Act: 0.0353. Min Act: -0.0006

Data Index: 669539 (C4 (Web Text))

Max Activating Token Index: 185

Text #7

Max Range: 0.0409. Min Range: -0.0409

Max Act: 0.0375. Min Act: -0.0006

Data Index: 848674 (C4 (Web Text))

Max Activating Token Index: 760

Text #8

Max Range: 0.0409. Min Range: -0.0409

Max Act: 0.0360. Min Act: -0.0006

Data Index: 263562 (C4 (Web Text))

Max Activating Token Index: 428

Text #9

Max Range: 0.0409. Min Range: -0.0409

Max Act: 0.0356. Min Act: -0.0006

Data Index: 989100 (C4 (Web Text))

Max Activating Token Index: 30

Text #10

Max Range: 0.0409. Min Range: -0.0409

Max Act: 0.0355. Min Act: -0.0006

Data Index: 60889 (C4 (Web Text))

Max Activating Token Index: 378

Text #11

Max Range: 0.0409. Min Range: -0.0409

Max Act: 0.0361. Min Act: -0.0006

Data Index: 790108 (C4 (Web Text))

Max Activating Token Index: 449

Text #12

Max Range: 0.0409. Min Range: -0.0409

Max Act: 0.0350. Min Act: -0.0006

Data Index: 105769 (C4 (Web Text))

Max Activating Token Index: 743

Text #13

Max Range: 0.0409. Min Range: -0.0409

Max Act: 0.0349. Min Act: -0.0006

Data Index: 1295782 (C4 (Web Text))

Max Activating Token Index: 22

Text #14

Max Range: 0.0409. Min Range: -0.0409

Max Act: 0.0325. Min Act: -0.0006

Data Index: 1118148 (C4 (Web Text))

Max Activating Token Index: 977

Text #15

Max Range: 0.0409. Min Range: -0.0409

Max Act: 0.0340. Min Act: -0.0006

Data Index: 279808 (C4 (Web Text))

Max Activating Token Index: 329

Text #16

Max Range: 0.0409. Min Range: -0.0409

Max Act: 0.0336. Min Act: -0.0006

Data Index: 1024566 (C4 (Web Text))

Max Activating Token Index: 332

Text #17

Max Range: 0.0409. Min Range: -0.0409

Max Act: 0.0349. Min Act: -0.0006

Data Index: 686950 (C4 (Web Text))

Max Activating Token Index: 468

Text #18

Max Range: 0.0409. Min Range: -0.0409

Max Act: 0.0330. Min Act: -0.0006

Data Index: 915731 (C4 (Web Text))

Max Activating Token Index: 117

Text #19

Max Range: 0.0409. Min Range: -0.0409

Max Act: 0.0343. Min Act: -0.0006

Data Index: 481476 (C4 (Web Text))

Max Activating Token Index: 56