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

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

Neuron 728 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: 0.3934. Min Range: -0.3934

Max Act: 0.3934. Min Act: -0.0001

Data Index: 126741 (C4 (Web Text))

Max Activating Token Index: 274

Text #1

Max Range: 0.3934. Min Range: -0.3934

Max Act: 0.2956. Min Act: -0.0001

Data Index: 1330104 (C4 (Web Text))

Max Activating Token Index: 431

Text #2

Max Range: 0.3934. Min Range: -0.3934

Max Act: 0.3080. Min Act: -0.0001

Data Index: 1069917 (C4 (Web Text))

Max Activating Token Index: 392

Text #3

Max Range: 0.3934. Min Range: -0.3934

Max Act: 0.2758. Min Act: -0.0001

Data Index: 588821 (C4 (Web Text))

Max Activating Token Index: 537

Text #4

Max Range: 0.3934. Min Range: -0.3934

Max Act: 0.2587. Min Act: -0.0001

Data Index: 75369 (C4 (Web Text))

Max Activating Token Index: 987

Text #5

Max Range: 0.3934. Min Range: -0.3934

Max Act: 0.2614. Min Act: -0.0001

Data Index: 1230748 (C4 (Web Text))

Max Activating Token Index: 493

Text #6

Max Range: 0.3934. Min Range: -0.3934

Max Act: 0.2708. Min Act: -0.0001

Data Index: 1170139 (C4 (Web Text))

Max Activating Token Index: 216

Text #7

Max Range: 0.3934. Min Range: -0.3934

Max Act: 0.2274. Min Act: -0.0001

Data Index: 1304033 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.3934. Min Range: -0.3934

Max Act: 0.2256. Min Act: -0.0001

Data Index: 1230008 (C4 (Web Text))

Max Activating Token Index: 547

Text #9

Max Range: 0.3934. Min Range: -0.3934

Max Act: 0.2483. Min Act: -0.0001

Data Index: 1093173 (C4 (Web Text))

Max Activating Token Index: 221

Text #10

Max Range: 0.3934. Min Range: -0.3934

Max Act: 0.2428. Min Act: -0.0001

Data Index: 1028509 (C4 (Web Text))

Max Activating Token Index: 547

Text #11

Max Range: 0.3934. Min Range: -0.3934

Max Act: 0.2460. Min Act: -0.0001

Data Index: 816915 (C4 (Web Text))

Max Activating Token Index: 301

Text #12

Max Range: 0.3934. Min Range: -0.3934

Max Act: 0.2285. Min Act: -0.0001

Data Index: 149885 (C4 (Web Text))

Max Activating Token Index: 816

Text #13

Max Range: 0.3934. Min Range: -0.3934

Max Act: 0.2349. Min Act: -0.0001

Data Index: 755274 (C4 (Web Text))

Max Activating Token Index: 790

Text #14

Max Range: 0.3934. Min Range: -0.3934

Max Act: 0.2164. Min Act: -0.0001

Data Index: 1284344 (C4 (Web Text))

Max Activating Token Index: 803

Text #15

Max Range: 0.3934. Min Range: -0.3934

Max Act: 0.2245. Min Act: -0.0001

Data Index: 391532 (C4 (Web Text))

Max Activating Token Index: 500

Text #16

Max Range: 0.3934. Min Range: -0.3934

Max Act: 0.2144. Min Act: -0.0001

Data Index: 824435 (C4 (Web Text))

Max Activating Token Index: 941

Text #17

Max Range: 0.3934. Min Range: -0.3934

Max Act: 0.2196. Min Act: -0.0001

Data Index: 554517 (C4 (Web Text))

Max Activating Token Index: 456

Text #18

Max Range: 0.3934. Min Range: -0.3934

Max Act: 0.2187. Min Act: -0.0001

Data Index: 443412 (C4 (Web Text))

Max Activating Token Index: 340

Text #19

Max Range: 0.3934. Min Range: -0.3934

Max Act: 0.2168. Min Act: -0.0001

Data Index: 728241 (C4 (Web Text))

Max Activating Token Index: 846