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

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

Neuron 1292 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: 1.4555. Min Range: -1.4555

Max Act: 1.4555. Min Act: -0.0002

Data Index: 983107 (C4 (Web Text))

Max Activating Token Index: 42

Text #1

Max Range: 1.4555. Min Range: -1.4555

Max Act: 1.3737. Min Act: -0.0002

Data Index: 1262471 (C4 (Web Text))

Max Activating Token Index: 48

Text #2

Max Range: 1.4555. Min Range: -1.4555

Max Act: 1.3274. Min Act: -0.0003

Data Index: 253891 (C4 (Web Text))

Max Activating Token Index: 794

Text #3

Max Range: 1.4555. Min Range: -1.4555

Max Act: 1.3071. Min Act: -0.0002

Data Index: 1074122 (C4 (Web Text))

Max Activating Token Index: 752

Text #4

Max Range: 1.4555. Min Range: -1.4555

Max Act: 1.3195. Min Act: -0.0002

Data Index: 214087 (C4 (Web Text))

Max Activating Token Index: 466

Text #5

Max Range: 1.4555. Min Range: -1.4555

Max Act: 1.2963. Min Act: -0.0002

Data Index: 1294214 (C4 (Web Text))

Max Activating Token Index: 360

Text #6

Max Range: 1.4555. Min Range: -1.4555

Max Act: 1.2949. Min Act: -0.0002

Data Index: 46935 (C4 (Web Text))

Max Activating Token Index: 214

Text #7

Max Range: 1.4555. Min Range: -1.4555

Max Act: 1.2882. Min Act: -0.0002

Data Index: 1334299 (C4 (Web Text))

Max Activating Token Index: 526

Text #8

Max Range: 1.4555. Min Range: -1.4555

Max Act: 1.3059. Min Act: -0.0002

Data Index: 564072 (C4 (Web Text))

Max Activating Token Index: 127

Text #9

Max Range: 1.4555. Min Range: -1.4555

Max Act: 1.2988. Min Act: -0.0002

Data Index: 605470 (C4 (Web Text))

Max Activating Token Index: 155

Text #10

Max Range: 1.4555. Min Range: -1.4555

Max Act: 1.2707. Min Act: -0.0002

Data Index: 433876 (C4 (Web Text))

Max Activating Token Index: 31

Text #11

Max Range: 1.4555. Min Range: -1.4555

Max Act: 1.2247. Min Act: -0.0002

Data Index: 845238 (C4 (Web Text))

Max Activating Token Index: 749

Text #12

Max Range: 1.4555. Min Range: -1.4555

Max Act: 1.2298. Min Act: -0.0002

Data Index: 821769 (C4 (Web Text))

Max Activating Token Index: 272

Text #13

Max Range: 1.4555. Min Range: -1.4555

Max Act: 1.2270. Min Act: -0.0002

Data Index: 376775 (C4 (Web Text))

Max Activating Token Index: 527

Text #14

Max Range: 1.4555. Min Range: -1.4555

Max Act: 1.2047. Min Act: -0.0002

Data Index: 162862 (C4 (Web Text))

Max Activating Token Index: 36

Text #15

Max Range: 1.4555. Min Range: -1.4555

Max Act: 1.1911. Min Act: -0.0002

Data Index: 552229 (C4 (Web Text))

Max Activating Token Index: 20

Text #16

Max Range: 1.4555. Min Range: -1.4555

Max Act: 1.1834. Min Act: -0.0002

Data Index: 361305 (C4 (Web Text))

Max Activating Token Index: 50

Text #17

Max Range: 1.4555. Min Range: -1.4555

Max Act: 1.1752. Min Act: -0.0002

Data Index: 1319354 (C4 (Web Text))

Max Activating Token Index: 83

Text #18

Max Range: 1.4555. Min Range: -1.4555

Max Act: 1.1678. Min Act: -0.0002

Data Index: 181808 (C4 (Web Text))

Max Activating Token Index: 624

Text #19

Max Range: 1.4555. Min Range: -1.4555

Max Act: 1.1761. Min Act: -0.0002

Data Index: 1002397 (C4 (Web Text))

Max Activating Token Index: 809