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

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

Neuron 3179 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7443. Min Range: -0.7443

Max Act: 0.7443. Min Act: -0.0003

Data Index: 586160 (C4 (Web Text))

Max Activating Token Index: 19

Text #1

Max Range: 0.7443. Min Range: -0.7443

Max Act: 0.6215. Min Act: -0.0003

Data Index: 198462 (C4 (Web Text))

Max Activating Token Index: 89

Text #2

Max Range: 0.7443. Min Range: -0.7443

Max Act: 0.5584. Min Act: -0.0003

Data Index: 384722 (C4 (Web Text))

Max Activating Token Index: 159

Text #3

Max Range: 0.7443. Min Range: -0.7443

Max Act: 0.5543. Min Act: -0.0003

Data Index: 753377 (C4 (Web Text))

Max Activating Token Index: 170

Text #4

Max Range: 0.7443. Min Range: -0.7443

Max Act: 0.5510. Min Act: -0.0002

Data Index: 965570 (C4 (Web Text))

Max Activating Token Index: 15

Text #5

Max Range: 0.7443. Min Range: -0.7443

Max Act: 0.5310. Min Act: -0.0003

Data Index: 25499 (C4 (Web Text))

Max Activating Token Index: 92

Text #6

Max Range: 0.7443. Min Range: -0.7443

Max Act: 0.5286. Min Act: -0.0003

Data Index: 627416 (C4 (Web Text))

Max Activating Token Index: 40

Text #7

Max Range: 0.7443. Min Range: -0.7443

Max Act: 0.4738. Min Act: -0.0003

Data Index: 6230 (C4 (Web Text))

Max Activating Token Index: 206

Text #8

Max Range: 0.7443. Min Range: -0.7443

Max Act: 0.4883. Min Act: -0.0003

Data Index: 1205483 (C4 (Web Text))

Max Activating Token Index: 122

Text #9

Max Range: 0.7443. Min Range: -0.7443

Max Act: 0.4705. Min Act: -0.0003

Data Index: 763245 (C4 (Web Text))

Max Activating Token Index: 543

Text #10

Max Range: 0.7443. Min Range: -0.7443

Max Act: 0.4637. Min Act: -0.0003

Data Index: 486720 (C4 (Web Text))

Max Activating Token Index: 51

Text #11

Max Range: 0.7443. Min Range: -0.7443

Max Act: 0.4522. Min Act: -0.0003

Data Index: 827846 (C4 (Web Text))

Max Activating Token Index: 433

Text #12

Max Range: 0.7443. Min Range: -0.7443

Max Act: 0.4501. Min Act: -0.0003

Data Index: 737545 (C4 (Web Text))

Max Activating Token Index: 172

Text #13

Max Range: 0.7443. Min Range: -0.7443

Max Act: 0.4440. Min Act: -0.0003

Data Index: 918716 (C4 (Web Text))

Max Activating Token Index: 811

Text #14

Max Range: 0.7443. Min Range: -0.7443

Max Act: 0.4425. Min Act: -0.0003

Data Index: 350399 (C4 (Web Text))

Max Activating Token Index: 214

Text #15

Max Range: 0.7443. Min Range: -0.7443

Max Act: 0.4405. Min Act: -0.0003

Data Index: 843830 (C4 (Web Text))

Max Activating Token Index: 25

Text #16

Max Range: 0.7443. Min Range: -0.7443

Max Act: 0.4256. Min Act: -0.0003

Data Index: 540599 (C4 (Web Text))

Max Activating Token Index: 177

Text #17

Max Range: 0.7443. Min Range: -0.7443

Max Act: 0.4250. Min Act: -0.0003

Data Index: 121607 (C4 (Web Text))

Max Activating Token Index: 60

Text #18

Max Range: 0.7443. Min Range: -0.7443

Max Act: 0.4189. Min Act: -0.0003

Data Index: 332541 (C4 (Web Text))

Max Activating Token Index: 407

Text #19

Max Range: 0.7443. Min Range: -0.7443

Max Act: 0.4120. Min Act: -0.0003

Data Index: 338651 (C4 (Web Text))

Max Activating Token Index: 18