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

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

Neuron 3893 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: 0.9395. Min Range: -0.9395

Max Act: 0.9395. Min Act: -0.0000

Data Index: 617502 (C4 (Web Text))

Max Activating Token Index: 241

Text #1

Max Range: 0.9395. Min Range: -0.9395

Max Act: 0.8905. Min Act: -0.0001

Data Index: 987217 (C4 (Web Text))

Max Activating Token Index: 53

Text #2

Max Range: 0.9395. Min Range: -0.9395

Max Act: 0.8726. Min Act: -0.0001

Data Index: 959175 (C4 (Web Text))

Max Activating Token Index: 111

Text #3

Max Range: 0.9395. Min Range: -0.9395

Max Act: 0.8749. Min Act: -0.0000

Data Index: 484964 (C4 (Web Text))

Max Activating Token Index: 256

Text #4

Max Range: 0.9395. Min Range: -0.9395

Max Act: 0.8029. Min Act: -0.0000

Data Index: 68493 (C4 (Web Text))

Max Activating Token Index: 174

Text #5

Max Range: 0.9395. Min Range: -0.9395

Max Act: 0.8219. Min Act: -0.0000

Data Index: 256647 (C4 (Web Text))

Max Activating Token Index: 168

Text #6

Max Range: 0.9395. Min Range: -0.9395

Max Act: 0.8234. Min Act: -0.0000

Data Index: 294630 (C4 (Web Text))

Max Activating Token Index: 136

Text #7

Max Range: 0.9395. Min Range: -0.9395

Max Act: 0.7635. Min Act: -0.0000

Data Index: 1357151 (C4 (Web Text))

Max Activating Token Index: 72

Text #8

Max Range: 0.9395. Min Range: -0.9395

Max Act: 0.7627. Min Act: -0.0001

Data Index: 1186798 (C4 (Web Text))

Max Activating Token Index: 274

Text #9

Max Range: 0.9395. Min Range: -0.9395

Max Act: 0.7570. Min Act: -0.0000

Data Index: 246725 (C4 (Web Text))

Max Activating Token Index: 193

Text #10

Max Range: 0.9395. Min Range: -0.9395

Max Act: 0.8494. Min Act: -0.0001

Data Index: 1120669 (C4 (Web Text))

Max Activating Token Index: 108

Text #11

Max Range: 0.9395. Min Range: -0.9395

Max Act: 0.7428. Min Act: -0.0001

Data Index: 274873 (C4 (Web Text))

Max Activating Token Index: 138

Text #12

Max Range: 0.9395. Min Range: -0.9395

Max Act: 0.7809. Min Act: -0.0000

Data Index: 30226 (C4 (Web Text))

Max Activating Token Index: 112

Text #13

Max Range: 0.9395. Min Range: -0.9395

Max Act: 0.7412. Min Act: -0.0000

Data Index: 592242 (C4 (Web Text))

Max Activating Token Index: 208

Text #14

Max Range: 0.9395. Min Range: -0.9395

Max Act: 0.7616. Min Act: -0.0001

Data Index: 302934 (C4 (Web Text))

Max Activating Token Index: 301

Text #15

Max Range: 0.9395. Min Range: -0.9395

Max Act: 0.7654. Min Act: -0.0000

Data Index: 432533 (C4 (Web Text))

Max Activating Token Index: 153

Text #16

Max Range: 0.9395. Min Range: -0.9395

Max Act: 0.7285. Min Act: -0.0001

Data Index: 654109 (C4 (Web Text))

Max Activating Token Index: 194

Text #17

Max Range: 0.9395. Min Range: -0.9395

Max Act: 0.7702. Min Act: -0.0000

Data Index: 876305 (C4 (Web Text))

Max Activating Token Index: 156

Text #18

Max Range: 0.9395. Min Range: -0.9395

Max Act: 0.7084. Min Act: -0.0001

Data Index: 549891 (C4 (Web Text))

Max Activating Token Index: 264

Text #19

Max Range: 0.9395. Min Range: -0.9395

Max Act: 0.7234. Min Act: -0.0001

Data Index: 696842 (C4 (Web Text))

Max Activating Token Index: 278