Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1361 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.3020. Min Range: -1.3020

Max Act: 1.3020. Min Act: -0.0000

Data Index: 670063 (C4 (Web Text))

Max Activating Token Index: 129

Text #1

Max Range: 1.3020. Min Range: -1.3020

Max Act: 1.2893. Min Act: -0.0000

Data Index: 1049263 (C4 (Web Text))

Max Activating Token Index: 20

Text #2

Max Range: 1.3020. Min Range: -1.3020

Max Act: 1.2260. Min Act: -0.0000

Data Index: 629234 (C4 (Web Text))

Max Activating Token Index: 784

Text #3

Max Range: 1.3020. Min Range: -1.3020

Max Act: 1.2358. Min Act: -0.0000

Data Index: 514390 (C4 (Web Text))

Max Activating Token Index: 619

Text #4

Max Range: 1.3020. Min Range: -1.3020

Max Act: 1.2205. Min Act: -0.0000

Data Index: 1221243 (C4 (Web Text))

Max Activating Token Index: 854

Text #5

Max Range: 1.3020. Min Range: -1.3020

Max Act: 0.9222. Min Act: -0.0000

Data Index: 524952 (C4 (Web Text))

Max Activating Token Index: 760

Text #6

Max Range: 1.3020. Min Range: -1.3020

Max Act: 1.1150. Min Act: -0.0000

Data Index: 985858 (C4 (Web Text))

Max Activating Token Index: 895

Text #7

Max Range: 1.3020. Min Range: -1.3020

Max Act: 1.0335. Min Act: -0.0000

Data Index: 362045 (C4 (Web Text))

Max Activating Token Index: 766

Text #8

Max Range: 1.3020. Min Range: -1.3020

Max Act: 1.0248. Min Act: -0.0000

Data Index: 1016431 (C4 (Web Text))

Max Activating Token Index: 460

Text #9

Max Range: 1.3020. Min Range: -1.3020

Max Act: 0.9810. Min Act: -0.0000

Data Index: 147862 (C4 (Web Text))

Max Activating Token Index: 28

Text #10

Max Range: 1.3020. Min Range: -1.3020

Max Act: 0.9165. Min Act: -0.0000

Data Index: 348987 (C4 (Web Text))

Max Activating Token Index: 952

Text #11

Max Range: 1.3020. Min Range: -1.3020

Max Act: 0.9273. Min Act: -0.0000

Data Index: 782397 (C4 (Web Text))

Max Activating Token Index: 686

Text #12

Max Range: 1.3020. Min Range: -1.3020

Max Act: 0.9085. Min Act: -0.0000

Data Index: 189061 (C4 (Web Text))

Max Activating Token Index: 881

Text #13

Max Range: 1.3020. Min Range: -1.3020

Max Act: 0.8330. Min Act: -0.0000

Data Index: 193858 (C4 (Web Text))

Max Activating Token Index: 631

Text #14

Max Range: 1.3020. Min Range: -1.3020

Max Act: 0.8959. Min Act: -0.0000

Data Index: 96201 (C4 (Web Text))

Max Activating Token Index: 118

Text #15

Max Range: 1.3020. Min Range: -1.3020

Max Act: 0.7702. Min Act: -0.0000

Data Index: 440293 (C4 (Web Text))

Max Activating Token Index: 274

Text #16

Max Range: 1.3020. Min Range: -1.3020

Max Act: 0.8418. Min Act: -0.0000

Data Index: 459329 (C4 (Web Text))

Max Activating Token Index: 214

Text #17

Max Range: 1.3020. Min Range: -1.3020

Max Act: 0.8279. Min Act: -0.0000

Data Index: 849006 (C4 (Web Text))

Max Activating Token Index: 345

Text #18

Max Range: 1.3020. Min Range: -1.3020

Max Act: 0.7336. Min Act: -0.0000

Data Index: 211803 (C4 (Web Text))

Max Activating Token Index: 742

Text #19

Max Range: 1.3020. Min Range: -1.3020

Max Act: 0.8089. Min Act: -0.0000

Data Index: 656649 (C4 (Web Text))

Max Activating Token Index: 291