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

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

Neuron 3753 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0640. Min Act: -0.0002

Data Index: 1065161 (C4 (Web Text))

Max Activating Token Index: 818

Text #1

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0615. Min Act: -0.0001

Data Index: 8950 (C4 (Web Text))

Max Activating Token Index: 91

Text #2

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0605. Min Act: -0.0001

Data Index: 84279 (C4 (Web Text))

Max Activating Token Index: 866

Text #3

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0532. Min Act: -0.0002

Data Index: 400902 (C4 (Web Text))

Max Activating Token Index: 618

Text #4

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0526. Min Act: -0.0001

Data Index: 168977 (C4 (Web Text))

Max Activating Token Index: 90

Text #5

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0504. Min Act: -0.0001

Data Index: 1064293 (C4 (Web Text))

Max Activating Token Index: 167

Text #6

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0533. Min Act: -0.0002

Data Index: 544966 (C4 (Web Text))

Max Activating Token Index: 421

Text #7

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0532. Min Act: -0.0002

Data Index: 364368 (C4 (Web Text))

Max Activating Token Index: 1019

Text #8

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0503. Min Act: -0.0001

Data Index: 1580714 (Python Code)

Max Activating Token Index: 9

Text #9

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0500. Min Act: -0.0001

Data Index: 1031123 (C4 (Web Text))

Max Activating Token Index: 596

Text #10

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0511. Min Act: -0.0001

Data Index: 646441 (C4 (Web Text))

Max Activating Token Index: 525

Text #11

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0444. Min Act: -0.0001

Data Index: 963091 (C4 (Web Text))

Max Activating Token Index: 207

Text #12

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0469. Min Act: -0.0001

Data Index: 11436 (C4 (Web Text))

Max Activating Token Index: 51

Text #13

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0476. Min Act: -0.0001

Data Index: 1269862 (C4 (Web Text))

Max Activating Token Index: 216

Text #14

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0482. Min Act: -0.0001

Data Index: 772671 (C4 (Web Text))

Max Activating Token Index: 971

Text #15

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0489. Min Act: -0.0001

Data Index: 581445 (C4 (Web Text))

Max Activating Token Index: 569

Text #16

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0486. Min Act: -0.0001

Data Index: 38548 (C4 (Web Text))

Max Activating Token Index: 225

Text #17

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0459. Min Act: -0.0002

Data Index: 208475 (C4 (Web Text))

Max Activating Token Index: 23

Text #18

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0465. Min Act: -0.0002

Data Index: 454068 (C4 (Web Text))

Max Activating Token Index: 111

Text #19

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0449. Min Act: -0.0001

Data Index: 430310 (C4 (Web Text))

Max Activating Token Index: 782