Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5950 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.4961. Min Range: -1.4961

Max Act: 1.4961. Min Act: -0.0002

Data Index: 1216478 (C4 (Web Text))

Max Activating Token Index: 481

Text #1

Max Range: 1.4961. Min Range: -1.4961

Max Act: 1.4192. Min Act: -0.0002

Data Index: 535181 (C4 (Web Text))

Max Activating Token Index: 237

Text #2

Max Range: 1.4961. Min Range: -1.4961

Max Act: 1.4541. Min Act: -0.0002

Data Index: 364380 (C4 (Web Text))

Max Activating Token Index: 450

Text #3

Max Range: 1.4961. Min Range: -1.4961

Max Act: 1.4152. Min Act: -0.0002

Data Index: 389181 (C4 (Web Text))

Max Activating Token Index: 225

Text #4

Max Range: 1.4961. Min Range: -1.4961

Max Act: 1.3690. Min Act: -0.0002

Data Index: 200269 (C4 (Web Text))

Max Activating Token Index: 378

Text #5

Max Range: 1.4961. Min Range: -1.4961

Max Act: 1.3371. Min Act: -0.0002

Data Index: 427520 (C4 (Web Text))

Max Activating Token Index: 103

Text #6

Max Range: 1.4961. Min Range: -1.4961

Max Act: 1.2612. Min Act: -0.0002

Data Index: 502381 (C4 (Web Text))

Max Activating Token Index: 294

Text #7

Max Range: 1.4961. Min Range: -1.4961

Max Act: 1.2941. Min Act: -0.0002

Data Index: 373615 (C4 (Web Text))

Max Activating Token Index: 711

Text #8

Max Range: 1.4961. Min Range: -1.4961

Max Act: 1.2956. Min Act: -0.0002

Data Index: 56331 (C4 (Web Text))

Max Activating Token Index: 222

Text #9

Max Range: 1.4961. Min Range: -1.4961

Max Act: 1.3151. Min Act: -0.0002

Data Index: 521669 (C4 (Web Text))

Max Activating Token Index: 329

Text #10

Max Range: 1.4961. Min Range: -1.4961

Max Act: 1.2389. Min Act: -0.0002

Data Index: 1201519 (C4 (Web Text))

Max Activating Token Index: 534

Text #11

Max Range: 1.4961. Min Range: -1.4961

Max Act: 1.3165. Min Act: -0.0002

Data Index: 270305 (C4 (Web Text))

Max Activating Token Index: 307

Text #12

Max Range: 1.4961. Min Range: -1.4961

Max Act: 1.2594. Min Act: -0.0002

Data Index: 36677 (C4 (Web Text))

Max Activating Token Index: 243

Text #13

Max Range: 1.4961. Min Range: -1.4961

Max Act: 1.2646. Min Act: -0.0002

Data Index: 224049 (C4 (Web Text))

Max Activating Token Index: 682

Text #14

Max Range: 1.4961. Min Range: -1.4961

Max Act: 1.2644. Min Act: -0.0001

Data Index: 106306 (C4 (Web Text))

Max Activating Token Index: 91

Text #15

Max Range: 1.4961. Min Range: -1.4961

Max Act: 1.2485. Min Act: -0.0002

Data Index: 420117 (C4 (Web Text))

Max Activating Token Index: 261

Text #16

Max Range: 1.4961. Min Range: -1.4961

Max Act: 1.2497. Min Act: -0.0002

Data Index: 1182305 (C4 (Web Text))

Max Activating Token Index: 625

Text #17

Max Range: 1.4961. Min Range: -1.4961

Max Act: 1.2105. Min Act: -0.0002

Data Index: 1147878 (C4 (Web Text))

Max Activating Token Index: 605

Text #18

Max Range: 1.4961. Min Range: -1.4961

Max Act: 1.2040. Min Act: -0.0002

Data Index: 1348731 (C4 (Web Text))

Max Activating Token Index: 680

Text #19

Max Range: 1.4961. Min Range: -1.4961

Max Act: 1.2301. Min Act: -0.0002

Data Index: 1338042 (C4 (Web Text))

Max Activating Token Index: 228