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

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

Neuron 5437 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3924. Min Range: -0.3924

Max Act: 0.3924. Min Act: -0.0001

Data Index: 269035 (C4 (Web Text))

Max Activating Token Index: 439

Text #1

Max Range: 0.3924. Min Range: -0.3924

Max Act: 0.3449. Min Act: -0.0001

Data Index: 1183747 (C4 (Web Text))

Max Activating Token Index: 590

Text #2

Max Range: 0.3924. Min Range: -0.3924

Max Act: 0.3404. Min Act: -0.0001

Data Index: 1348908 (C4 (Web Text))

Max Activating Token Index: 472

Text #3

Max Range: 0.3924. Min Range: -0.3924

Max Act: 0.2769. Min Act: -0.0001

Data Index: 987114 (C4 (Web Text))

Max Activating Token Index: 475

Text #4

Max Range: 0.3924. Min Range: -0.3924

Max Act: 0.2759. Min Act: -0.0001

Data Index: 908489 (C4 (Web Text))

Max Activating Token Index: 243

Text #5

Max Range: 0.3924. Min Range: -0.3924

Max Act: 0.2624. Min Act: -0.0001

Data Index: 1316898 (C4 (Web Text))

Max Activating Token Index: 583

Text #6

Max Range: 0.3924. Min Range: -0.3924

Max Act: 0.2734. Min Act: -0.0001

Data Index: 474242 (C4 (Web Text))

Max Activating Token Index: 386

Text #7

Max Range: 0.3924. Min Range: -0.3924

Max Act: 0.2492. Min Act: -0.0001

Data Index: 825919 (C4 (Web Text))

Max Activating Token Index: 406

Text #8

Max Range: 0.3924. Min Range: -0.3924

Max Act: 0.2480. Min Act: -0.0001

Data Index: 1309286 (C4 (Web Text))

Max Activating Token Index: 458

Text #9

Max Range: 0.3924. Min Range: -0.3924

Max Act: 0.2301. Min Act: -0.0001

Data Index: 1075048 (C4 (Web Text))

Max Activating Token Index: 402

Text #10

Max Range: 0.3924. Min Range: -0.3924

Max Act: 0.2447. Min Act: -0.0001

Data Index: 1350824 (C4 (Web Text))

Max Activating Token Index: 439

Text #11

Max Range: 0.3924. Min Range: -0.3924

Max Act: 0.2289. Min Act: -0.0001

Data Index: 742117 (C4 (Web Text))

Max Activating Token Index: 896

Text #12

Max Range: 0.3924. Min Range: -0.3924

Max Act: 0.2311. Min Act: -0.0001

Data Index: 1106384 (C4 (Web Text))

Max Activating Token Index: 212

Text #13

Max Range: 0.3924. Min Range: -0.3924

Max Act: 0.2302. Min Act: -0.0001

Data Index: 278023 (C4 (Web Text))

Max Activating Token Index: 179

Text #14

Max Range: 0.3924. Min Range: -0.3924

Max Act: 0.2332. Min Act: -0.0001

Data Index: 506066 (C4 (Web Text))

Max Activating Token Index: 215

Text #15

Max Range: 0.3924. Min Range: -0.3924

Max Act: 0.2191. Min Act: -0.0001

Data Index: 452960 (C4 (Web Text))

Max Activating Token Index: 51

Text #16

Max Range: 0.3924. Min Range: -0.3924

Max Act: 0.2270. Min Act: -0.0001

Data Index: 1197063 (C4 (Web Text))

Max Activating Token Index: 470

Text #17

Max Range: 0.3924. Min Range: -0.3924

Max Act: 0.2019. Min Act: -0.0001

Data Index: 1313506 (C4 (Web Text))

Max Activating Token Index: 295

Text #18

Max Range: 0.3924. Min Range: -0.3924

Max Act: 0.2047. Min Act: -0.0001

Data Index: 599214 (C4 (Web Text))

Max Activating Token Index: 25

Text #19

Max Range: 0.3924. Min Range: -0.3924

Max Act: 0.2114. Min Act: -0.0001

Data Index: 474675 (C4 (Web Text))

Max Activating Token Index: 61