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

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

Neuron 2544 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5255. Min Range: -3.5255

Max Act: 3.5255. Min Act: -0.0000

Data Index: 283954 (C4 (Web Text))

Max Activating Token Index: 80

Text #1

Max Range: 3.5255. Min Range: -3.5255

Max Act: 3.3906. Min Act: -0.0000

Data Index: 708899 (C4 (Web Text))

Max Activating Token Index: 461

Text #2

Max Range: 3.5255. Min Range: -3.5255

Max Act: 3.3554. Min Act: -0.0000

Data Index: 435473 (C4 (Web Text))

Max Activating Token Index: 3

Text #3

Max Range: 3.5255. Min Range: -3.5255

Max Act: 3.1209. Min Act: -0.0000

Data Index: 829410 (C4 (Web Text))

Max Activating Token Index: 15

Text #4

Max Range: 3.5255. Min Range: -3.5255

Max Act: 3.2140. Min Act: -0.0000

Data Index: 261083 (C4 (Web Text))

Max Activating Token Index: 531

Text #5

Max Range: 3.5255. Min Range: -3.5255

Max Act: 3.2391. Min Act: -0.0000

Data Index: 1578336 (Python Code)

Max Activating Token Index: 888

Text #6

Max Range: 3.5255. Min Range: -3.5255

Max Act: 2.9998. Min Act: -0.0000

Data Index: 373973 (C4 (Web Text))

Max Activating Token Index: 334

Text #7

Max Range: 3.5255. Min Range: -3.5255

Max Act: 3.0214. Min Act: -0.0000

Data Index: 1327508 (C4 (Web Text))

Max Activating Token Index: 82

Text #8

Max Range: 3.5255. Min Range: -3.5255

Max Act: 2.8221. Min Act: -0.0000

Data Index: 1038250 (C4 (Web Text))

Max Activating Token Index: 907

Text #9

Max Range: 3.5255. Min Range: -3.5255

Max Act: 2.7807. Min Act: -0.0000

Data Index: 819799 (C4 (Web Text))

Max Activating Token Index: 639

Text #10

Max Range: 3.5255. Min Range: -3.5255

Max Act: 2.7715. Min Act: -0.0000

Data Index: 848357 (C4 (Web Text))

Max Activating Token Index: 135

Text #11

Max Range: 3.5255. Min Range: -3.5255

Max Act: 3.0189. Min Act: -0.0000

Data Index: 1256733 (C4 (Web Text))

Max Activating Token Index: 665

Text #12

Max Range: 3.5255. Min Range: -3.5255

Max Act: 2.8821. Min Act: -0.0000

Data Index: 1347772 (C4 (Web Text))

Max Activating Token Index: 333

Text #13

Max Range: 3.5255. Min Range: -3.5255

Max Act: 2.7202. Min Act: -0.0000

Data Index: 793498 (C4 (Web Text))

Max Activating Token Index: 452

Text #14

Max Range: 3.5255. Min Range: -3.5255

Max Act: 2.8573. Min Act: -0.0000

Data Index: 926234 (C4 (Web Text))

Max Activating Token Index: 21

Text #15

Max Range: 3.5255. Min Range: -3.5255

Max Act: 2.8192. Min Act: -0.0000

Data Index: 943900 (C4 (Web Text))

Max Activating Token Index: 330

Text #16

Max Range: 3.5255. Min Range: -3.5255

Max Act: 2.9420. Min Act: -0.0000

Data Index: 987174 (C4 (Web Text))

Max Activating Token Index: 583

Text #17

Max Range: 3.5255. Min Range: -3.5255

Max Act: 2.6545. Min Act: -0.0000

Data Index: 669304 (C4 (Web Text))

Max Activating Token Index: 910

Text #18

Max Range: 3.5255. Min Range: -3.5255

Max Act: 2.9454. Min Act: -0.0000

Data Index: 1375323 (Python Code)

Max Activating Token Index: 216

Text #19

Max Range: 3.5255. Min Range: -3.5255

Max Act: 3.0820. Min Act: -0.0000

Data Index: 923460 (C4 (Web Text))

Max Activating Token Index: 911