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

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

Neuron 3663 in Layer 0

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: 0.2421. Min Range: -0.2421

Max Act: 0.2409. Min Act: -0.0001

Data Index: 962900 (C4 (Web Text))

Max Activating Token Index: 395

Text #1

Max Range: 0.2421. Min Range: -0.2421

Max Act: 0.2403. Min Act: -0.0001

Data Index: 250800 (C4 (Web Text))

Max Activating Token Index: 177

Text #2

Max Range: 0.2421. Min Range: -0.2421

Max Act: 0.2421. Min Act: -0.0001

Data Index: 1041883 (C4 (Web Text))

Max Activating Token Index: 34

Text #3

Max Range: 0.2421. Min Range: -0.2421

Max Act: 0.2347. Min Act: -0.0001

Data Index: 155571 (C4 (Web Text))

Max Activating Token Index: 128

Text #4

Max Range: 0.2421. Min Range: -0.2421

Max Act: 0.2311. Min Act: -0.0001

Data Index: 1002286 (C4 (Web Text))

Max Activating Token Index: 553

Text #5

Max Range: 0.2421. Min Range: -0.2421

Max Act: 0.2262. Min Act: -0.0001

Data Index: 652066 (C4 (Web Text))

Max Activating Token Index: 384

Text #6

Max Range: 0.2421. Min Range: -0.2421

Max Act: 0.2259. Min Act: -0.0001

Data Index: 1164658 (C4 (Web Text))

Max Activating Token Index: 267

Text #7

Max Range: 0.2421. Min Range: -0.2421

Max Act: 0.2288. Min Act: -0.0001

Data Index: 1198643 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.2421. Min Range: -0.2421

Max Act: 0.2241. Min Act: -0.0001

Data Index: 167075 (C4 (Web Text))

Max Activating Token Index: 1002

Text #9

Max Range: 0.2421. Min Range: -0.2421

Max Act: 0.2219. Min Act: -0.0001

Data Index: 948244 (C4 (Web Text))

Max Activating Token Index: 81

Text #10

Max Range: 0.2421. Min Range: -0.2421

Max Act: 0.2191. Min Act: -0.0001

Data Index: 1212040 (C4 (Web Text))

Max Activating Token Index: 921

Text #11

Max Range: 0.2421. Min Range: -0.2421

Max Act: 0.2227. Min Act: -0.0001

Data Index: 750074 (C4 (Web Text))

Max Activating Token Index: 213

Text #12

Max Range: 0.2421. Min Range: -0.2421

Max Act: 0.2219. Min Act: -0.0001

Data Index: 1032520 (C4 (Web Text))

Max Activating Token Index: 454

Text #13

Max Range: 0.2421. Min Range: -0.2421

Max Act: 0.2181. Min Act: -0.0001

Data Index: 1197331 (C4 (Web Text))

Max Activating Token Index: 604

Text #14

Max Range: 0.2421. Min Range: -0.2421

Max Act: 0.2145. Min Act: -0.0001

Data Index: 702744 (C4 (Web Text))

Max Activating Token Index: 131

Text #15

Max Range: 0.2421. Min Range: -0.2421

Max Act: 0.2125. Min Act: -0.0001

Data Index: 344946 (C4 (Web Text))

Max Activating Token Index: 617

Text #16

Max Range: 0.2421. Min Range: -0.2421

Max Act: 0.2120. Min Act: -0.0001

Data Index: 542002 (C4 (Web Text))

Max Activating Token Index: 277

Text #17

Max Range: 0.2421. Min Range: -0.2421

Max Act: 0.2139. Min Act: -0.0001

Data Index: 469410 (C4 (Web Text))

Max Activating Token Index: 134

Text #18

Max Range: 0.2421. Min Range: -0.2421

Max Act: 0.2119. Min Act: -0.0001

Data Index: 926830 (C4 (Web Text))

Max Activating Token Index: 280

Text #19

Max Range: 0.2421. Min Range: -0.2421

Max Act: 0.2118. Min Act: -0.0001

Data Index: 1302313 (C4 (Web Text))

Max Activating Token Index: 692