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

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

Neuron 733 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8356. Min Range: -3.8356

Max Act: 3.8356. Min Act: -0.0000

Data Index: 1593354 (Python Code)

Max Activating Token Index: 691

Text #1

Max Range: 3.8356. Min Range: -3.8356

Max Act: 3.6249. Min Act: -0.0000

Data Index: 1302972 (C4 (Web Text))

Max Activating Token Index: 592

Text #2

Max Range: 3.8356. Min Range: -3.8356

Max Act: 3.3183. Min Act: -0.0000

Data Index: 357936 (C4 (Web Text))

Max Activating Token Index: 261

Text #3

Max Range: 3.8356. Min Range: -3.8356

Max Act: 3.2170. Min Act: -0.0000

Data Index: 146453 (C4 (Web Text))

Max Activating Token Index: 937

Text #4

Max Range: 3.8356. Min Range: -3.8356

Max Act: 3.1249. Min Act: -0.0000

Data Index: 1196340 (C4 (Web Text))

Max Activating Token Index: 267

Text #5

Max Range: 3.8356. Min Range: -3.8356

Max Act: 2.8568. Min Act: -0.0000

Data Index: 730803 (C4 (Web Text))

Max Activating Token Index: 380

Text #6

Max Range: 3.8356. Min Range: -3.8356

Max Act: 2.8230. Min Act: -0.0000

Data Index: 1606667 (Python Code)

Max Activating Token Index: 330

Text #7

Max Range: 3.8356. Min Range: -3.8356

Max Act: 2.7843. Min Act: -0.0000

Data Index: 194854 (C4 (Web Text))

Max Activating Token Index: 860

Text #8

Max Range: 3.8356. Min Range: -3.8356

Max Act: 2.7393. Min Act: -0.0000

Data Index: 615602 (C4 (Web Text))

Max Activating Token Index: 771

Text #9

Max Range: 3.8356. Min Range: -3.8356

Max Act: 2.5760. Min Act: -0.0000

Data Index: 1498561 (Python Code)

Max Activating Token Index: 983

Text #10

Max Range: 3.8356. Min Range: -3.8356

Max Act: 2.6826. Min Act: -0.0000

Data Index: 716786 (C4 (Web Text))

Max Activating Token Index: 820

Text #11

Max Range: 3.8356. Min Range: -3.8356

Max Act: 2.5191. Min Act: -0.0000

Data Index: 1379580 (Python Code)

Max Activating Token Index: 932

Text #12

Max Range: 3.8356. Min Range: -3.8356

Max Act: 2.5398. Min Act: -0.0000

Data Index: 1392356 (Python Code)

Max Activating Token Index: 700

Text #13

Max Range: 3.8356. Min Range: -3.8356

Max Act: 2.5300. Min Act: -0.0000

Data Index: 721070 (C4 (Web Text))

Max Activating Token Index: 374

Text #14

Max Range: 3.8356. Min Range: -3.8356

Max Act: 2.5084. Min Act: -0.0000

Data Index: 166331 (C4 (Web Text))

Max Activating Token Index: 924

Text #15

Max Range: 3.8356. Min Range: -3.8356

Max Act: 2.4932. Min Act: -0.0000

Data Index: 1580739 (Python Code)

Max Activating Token Index: 1008

Text #16

Max Range: 3.8356. Min Range: -3.8356

Max Act: 2.4588. Min Act: -0.0000

Data Index: 1202401 (C4 (Web Text))

Max Activating Token Index: 238

Text #17

Max Range: 3.8356. Min Range: -3.8356

Max Act: 2.4358. Min Act: -0.0000

Data Index: 1542840 (Python Code)

Max Activating Token Index: 828

Text #18

Max Range: 3.8356. Min Range: -3.8356

Max Act: 2.3878. Min Act: -0.0000

Data Index: 148227 (C4 (Web Text))

Max Activating Token Index: 348

Text #19

Max Range: 3.8356. Min Range: -3.8356

Max Act: 2.2753. Min Act: -0.0000

Data Index: 1388535 (Python Code)

Max Activating Token Index: 1017