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

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

Neuron 2973 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.0196. Min Range: -5.0196

Max Act: 5.0196. Min Act: -0.0001

Data Index: 640116 (C4 (Web Text))

Max Activating Token Index: 401

Text #1

Max Range: 5.0196. Min Range: -5.0196

Max Act: 4.1406. Min Act: -0.0001

Data Index: 33084 (C4 (Web Text))

Max Activating Token Index: 675

Text #2

Max Range: 5.0196. Min Range: -5.0196

Max Act: 4.2285. Min Act: -0.0001

Data Index: 404149 (C4 (Web Text))

Max Activating Token Index: 160

Text #3

Max Range: 5.0196. Min Range: -5.0196

Max Act: 3.7390. Min Act: -0.0001

Data Index: 259379 (C4 (Web Text))

Max Activating Token Index: 1000

Text #4

Max Range: 5.0196. Min Range: -5.0196

Max Act: 3.7247. Min Act: -0.0001

Data Index: 973714 (C4 (Web Text))

Max Activating Token Index: 432

Text #5

Max Range: 5.0196. Min Range: -5.0196

Max Act: 3.7342. Min Act: -0.0001

Data Index: 783377 (C4 (Web Text))

Max Activating Token Index: 484

Text #6

Max Range: 5.0196. Min Range: -5.0196

Max Act: 3.4932. Min Act: -0.0001

Data Index: 604329 (C4 (Web Text))

Max Activating Token Index: 590

Text #7

Max Range: 5.0196. Min Range: -5.0196

Max Act: 3.6621. Min Act: -0.0001

Data Index: 78843 (C4 (Web Text))

Max Activating Token Index: 798

Text #8

Max Range: 5.0196. Min Range: -5.0196

Max Act: 3.7369. Min Act: -0.0001

Data Index: 746909 (C4 (Web Text))

Max Activating Token Index: 469

Text #9

Max Range: 5.0196. Min Range: -5.0196

Max Act: 3.3217. Min Act: -0.0001

Data Index: 245877 (C4 (Web Text))

Max Activating Token Index: 529

Text #10

Max Range: 5.0196. Min Range: -5.0196

Max Act: 3.3356. Min Act: -0.0001

Data Index: 254391 (C4 (Web Text))

Max Activating Token Index: 368

Text #11

Max Range: 5.0196. Min Range: -5.0196

Max Act: 3.2755. Min Act: -0.0001

Data Index: 1261508 (C4 (Web Text))

Max Activating Token Index: 659

Text #12

Max Range: 5.0196. Min Range: -5.0196

Max Act: 3.0912. Min Act: -0.0001

Data Index: 452833 (C4 (Web Text))

Max Activating Token Index: 317

Text #13

Max Range: 5.0196. Min Range: -5.0196

Max Act: 3.5474. Min Act: -0.0001

Data Index: 713149 (C4 (Web Text))

Max Activating Token Index: 672

Text #14

Max Range: 5.0196. Min Range: -5.0196

Max Act: 3.0262. Min Act: -0.0001

Data Index: 1178750 (C4 (Web Text))

Max Activating Token Index: 321

Text #15

Max Range: 5.0196. Min Range: -5.0196

Max Act: 2.9951. Min Act: -0.0001

Data Index: 1141790 (C4 (Web Text))

Max Activating Token Index: 370

Text #16

Max Range: 5.0196. Min Range: -5.0196

Max Act: 2.9712. Min Act: -0.0001

Data Index: 32580 (C4 (Web Text))

Max Activating Token Index: 541

Text #17

Max Range: 5.0196. Min Range: -5.0196

Max Act: 2.9552. Min Act: -0.0001

Data Index: 1082234 (C4 (Web Text))

Max Activating Token Index: 154

Text #18

Max Range: 5.0196. Min Range: -5.0196

Max Act: 3.0992. Min Act: -0.0001

Data Index: 1304154 (C4 (Web Text))

Max Activating Token Index: 49

Text #19

Max Range: 5.0196. Min Range: -5.0196

Max Act: 3.1025. Min Act: -0.0001

Data Index: 508035 (C4 (Web Text))

Max Activating Token Index: 612