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

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

Neuron 3447 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: 1.5421. Min Range: -1.5421

Max Act: 1.5421. Min Act: -0.0002

Data Index: 1076211 (C4 (Web Text))

Max Activating Token Index: 791

Text #1

Max Range: 1.5421. Min Range: -1.5421

Max Act: 1.4593. Min Act: -0.0002

Data Index: 812811 (C4 (Web Text))

Max Activating Token Index: 36

Text #2

Max Range: 1.5421. Min Range: -1.5421

Max Act: 1.4991. Min Act: -0.0002

Data Index: 217933 (C4 (Web Text))

Max Activating Token Index: 65

Text #3

Max Range: 1.5421. Min Range: -1.5421

Max Act: 1.5057. Min Act: -0.0002

Data Index: 195276 (C4 (Web Text))

Max Activating Token Index: 261

Text #4

Max Range: 1.5421. Min Range: -1.5421

Max Act: 1.5298. Min Act: -0.0002

Data Index: 186177 (C4 (Web Text))

Max Activating Token Index: 432

Text #5

Max Range: 1.5421. Min Range: -1.5421

Max Act: 1.4504. Min Act: -0.0002

Data Index: 329557 (C4 (Web Text))

Max Activating Token Index: 479

Text #6

Max Range: 1.5421. Min Range: -1.5421

Max Act: 1.4117. Min Act: -0.0002

Data Index: 467600 (C4 (Web Text))

Max Activating Token Index: 362

Text #7

Max Range: 1.5421. Min Range: -1.5421

Max Act: 1.4350. Min Act: -0.0002

Data Index: 1172170 (C4 (Web Text))

Max Activating Token Index: 55

Text #8

Max Range: 1.5421. Min Range: -1.5421

Max Act: 1.4162. Min Act: -0.0002

Data Index: 237568 (C4 (Web Text))

Max Activating Token Index: 221

Text #9

Max Range: 1.5421. Min Range: -1.5421

Max Act: 1.4406. Min Act: -0.0002

Data Index: 460962 (C4 (Web Text))

Max Activating Token Index: 129

Text #10

Max Range: 1.5421. Min Range: -1.5421

Max Act: 1.4192. Min Act: -0.0002

Data Index: 573985 (C4 (Web Text))

Max Activating Token Index: 348

Text #11

Max Range: 1.5421. Min Range: -1.5421

Max Act: 1.3539. Min Act: -0.0002

Data Index: 924651 (C4 (Web Text))

Max Activating Token Index: 480

Text #12

Max Range: 1.5421. Min Range: -1.5421

Max Act: 1.3417. Min Act: -0.0002

Data Index: 600190 (C4 (Web Text))

Max Activating Token Index: 701

Text #13

Max Range: 1.5421. Min Range: -1.5421

Max Act: 1.3522. Min Act: -0.0002

Data Index: 677097 (C4 (Web Text))

Max Activating Token Index: 194

Text #14

Max Range: 1.5421. Min Range: -1.5421

Max Act: 1.3245. Min Act: -0.0002

Data Index: 763537 (C4 (Web Text))

Max Activating Token Index: 346

Text #15

Max Range: 1.5421. Min Range: -1.5421

Max Act: 1.3121. Min Act: -0.0002

Data Index: 1308233 (C4 (Web Text))

Max Activating Token Index: 26

Text #16

Max Range: 1.5421. Min Range: -1.5421

Max Act: 1.2900. Min Act: -0.0002

Data Index: 403078 (C4 (Web Text))

Max Activating Token Index: 520

Text #17

Max Range: 1.5421. Min Range: -1.5421

Max Act: 1.2623. Min Act: -0.0002

Data Index: 246838 (C4 (Web Text))

Max Activating Token Index: 232

Text #18

Max Range: 1.5421. Min Range: -1.5421

Max Act: 1.2851. Min Act: -0.0002

Data Index: 459945 (C4 (Web Text))

Max Activating Token Index: 481

Text #19

Max Range: 1.5421. Min Range: -1.5421

Max Act: 1.2646. Min Act: -0.0002

Data Index: 434869 (C4 (Web Text))

Max Activating Token Index: 336