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

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

Neuron 2007 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3318. Min Range: -0.3318

Max Act: 0.3318. Min Act: -0.0001

Data Index: 365175 (C4 (Web Text))

Max Activating Token Index: 190

Text #1

Max Range: 0.3318. Min Range: -0.3318

Max Act: 0.3072. Min Act: -0.0001

Data Index: 1305691 (C4 (Web Text))

Max Activating Token Index: 65

Text #2

Max Range: 0.3318. Min Range: -0.3318

Max Act: 0.3027. Min Act: -0.0001

Data Index: 151977 (C4 (Web Text))

Max Activating Token Index: 92

Text #3

Max Range: 0.3318. Min Range: -0.3318

Max Act: 0.2749. Min Act: -0.0001

Data Index: 1347808 (C4 (Web Text))

Max Activating Token Index: 541

Text #4

Max Range: 0.3318. Min Range: -0.3318

Max Act: 0.2621. Min Act: -0.0000

Data Index: 757600 (C4 (Web Text))

Max Activating Token Index: 51

Text #5

Max Range: 0.3318. Min Range: -0.3318

Max Act: 0.2395. Min Act: -0.0000

Data Index: 938561 (C4 (Web Text))

Max Activating Token Index: 144

Text #6

Max Range: 0.3318. Min Range: -0.3318

Max Act: 0.2018. Min Act: -0.0000

Data Index: 761397 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.3318. Min Range: -0.3318

Max Act: 0.1841. Min Act: -0.0001

Data Index: 359837 (C4 (Web Text))

Max Activating Token Index: 578

Text #8

Max Range: 0.3318. Min Range: -0.3318

Max Act: 0.1701. Min Act: -0.0000

Data Index: 700119 (C4 (Web Text))

Max Activating Token Index: 648

Text #9

Max Range: 0.3318. Min Range: -0.3318

Max Act: 0.1401. Min Act: -0.0001

Data Index: 1493163 (Python Code)

Max Activating Token Index: 711

Text #10

Max Range: 0.3318. Min Range: -0.3318

Max Act: 0.1702. Min Act: -0.0001

Data Index: 912334 (C4 (Web Text))

Max Activating Token Index: 540

Text #11

Max Range: 0.3318. Min Range: -0.3318

Max Act: 0.1652. Min Act: -0.0000

Data Index: 701711 (C4 (Web Text))

Max Activating Token Index: 987

Text #12

Max Range: 0.3318. Min Range: -0.3318

Max Act: 0.1572. Min Act: -0.0001

Data Index: 1424923 (Python Code)

Max Activating Token Index: 293

Text #13

Max Range: 0.3318. Min Range: -0.3318

Max Act: 0.1527. Min Act: -0.0001

Data Index: 247933 (C4 (Web Text))

Max Activating Token Index: 454

Text #14

Max Range: 0.3318. Min Range: -0.3318

Max Act: 0.1529. Min Act: -0.0001

Data Index: 682723 (C4 (Web Text))

Max Activating Token Index: 988

Text #15

Max Range: 0.3318. Min Range: -0.3318

Max Act: 0.1457. Min Act: -0.0000

Data Index: 473458 (C4 (Web Text))

Max Activating Token Index: 393

Text #16

Max Range: 0.3318. Min Range: -0.3318

Max Act: 0.1489. Min Act: -0.0001

Data Index: 565281 (C4 (Web Text))

Max Activating Token Index: 519

Text #17

Max Range: 0.3318. Min Range: -0.3318

Max Act: 0.1467. Min Act: -0.0000

Data Index: 167865 (C4 (Web Text))

Max Activating Token Index: 701

Text #18

Max Range: 0.3318. Min Range: -0.3318

Max Act: 0.1485. Min Act: -0.0001

Data Index: 330388 (C4 (Web Text))

Max Activating Token Index: 558

Text #19

Max Range: 0.3318. Min Range: -0.3318

Max Act: 0.1379. Min Act: -0.0001

Data Index: 74938 (C4 (Web Text))

Max Activating Token Index: 325