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

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

Neuron 3256 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.3437. Min Range: -0.3437

Max Act: 0.3437. Min Act: -0.0002

Data Index: 764311 (C4 (Web Text))

Max Activating Token Index: 571

Text #1

Max Range: 0.3437. Min Range: -0.3437

Max Act: 0.3288. Min Act: -0.0002

Data Index: 1248774 (C4 (Web Text))

Max Activating Token Index: 349

Text #2

Max Range: 0.3437. Min Range: -0.3437

Max Act: 0.3353. Min Act: -0.0002

Data Index: 859433 (C4 (Web Text))

Max Activating Token Index: 347

Text #3

Max Range: 0.3437. Min Range: -0.3437

Max Act: 0.3289. Min Act: -0.0002

Data Index: 1124472 (C4 (Web Text))

Max Activating Token Index: 350

Text #4

Max Range: 0.3437. Min Range: -0.3437

Max Act: 0.3280. Min Act: -0.0002

Data Index: 27272 (C4 (Web Text))

Max Activating Token Index: 522

Text #5

Max Range: 0.3437. Min Range: -0.3437

Max Act: 0.3274. Min Act: -0.0002

Data Index: 776961 (C4 (Web Text))

Max Activating Token Index: 21

Text #6

Max Range: 0.3437. Min Range: -0.3437

Max Act: 0.3237. Min Act: -0.0002

Data Index: 515956 (C4 (Web Text))

Max Activating Token Index: 810

Text #7

Max Range: 0.3437. Min Range: -0.3437

Max Act: 0.3231. Min Act: -0.0002

Data Index: 163521 (C4 (Web Text))

Max Activating Token Index: 967

Text #8

Max Range: 0.3437. Min Range: -0.3437

Max Act: 0.3172. Min Act: -0.0002

Data Index: 58870 (C4 (Web Text))

Max Activating Token Index: 207

Text #9

Max Range: 0.3437. Min Range: -0.3437

Max Act: 0.3220. Min Act: -0.0002

Data Index: 1122613 (C4 (Web Text))

Max Activating Token Index: 293

Text #10

Max Range: 0.3437. Min Range: -0.3437

Max Act: 0.3258. Min Act: -0.0002

Data Index: 267747 (C4 (Web Text))

Max Activating Token Index: 674

Text #11

Max Range: 0.3437. Min Range: -0.3437

Max Act: 0.3179. Min Act: -0.0002

Data Index: 1021391 (C4 (Web Text))

Max Activating Token Index: 1013

Text #12

Max Range: 0.3437. Min Range: -0.3437

Max Act: 0.3178. Min Act: -0.0002

Data Index: 1166132 (C4 (Web Text))

Max Activating Token Index: 1019

Text #13

Max Range: 0.3437. Min Range: -0.3437

Max Act: 0.3122. Min Act: -0.0002

Data Index: 434395 (C4 (Web Text))

Max Activating Token Index: 682

Text #14

Max Range: 0.3437. Min Range: -0.3437

Max Act: 0.3159. Min Act: -0.0003

Data Index: 1339327 (C4 (Web Text))

Max Activating Token Index: 295

Text #15

Max Range: 0.3437. Min Range: -0.3437

Max Act: 0.3167. Min Act: -0.0003

Data Index: 542658 (C4 (Web Text))

Max Activating Token Index: 846

Text #16

Max Range: 0.3437. Min Range: -0.3437

Max Act: 0.3156. Min Act: -0.0002

Data Index: 160989 (C4 (Web Text))

Max Activating Token Index: 887

Text #17

Max Range: 0.3437. Min Range: -0.3437

Max Act: 0.3175. Min Act: -0.0002

Data Index: 1278924 (C4 (Web Text))

Max Activating Token Index: 798

Text #18

Max Range: 0.3437. Min Range: -0.3437

Max Act: 0.3118. Min Act: -0.0003

Data Index: 528886 (C4 (Web Text))

Max Activating Token Index: 637

Text #19

Max Range: 0.3437. Min Range: -0.3437

Max Act: 0.3133. Min Act: -0.0002

Data Index: 1136225 (C4 (Web Text))

Max Activating Token Index: 986