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

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

Neuron 5084 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0399. Min Act: -0.0000

Data Index: 1183471 (C4 (Web Text))

Max Activating Token Index: 397

Text #1

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0367. Min Act: -0.0000

Data Index: 40972 (C4 (Web Text))

Max Activating Token Index: 29

Text #2

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0349. Min Act: -0.0000

Data Index: 1049849 (C4 (Web Text))

Max Activating Token Index: 67

Text #3

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0336. Min Act: -0.0000

Data Index: 555745 (C4 (Web Text))

Max Activating Token Index: 14

Text #4

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0350. Min Act: -0.0000

Data Index: 1017287 (C4 (Web Text))

Max Activating Token Index: 955

Text #5

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0289. Min Act: -0.0000

Data Index: 666589 (C4 (Web Text))

Max Activating Token Index: 538

Text #6

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0295. Min Act: -0.0000

Data Index: 985191 (C4 (Web Text))

Max Activating Token Index: 486

Text #7

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0284. Min Act: -0.0000

Data Index: 687553 (C4 (Web Text))

Max Activating Token Index: 476

Text #8

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0290. Min Act: -0.0000

Data Index: 1334969 (C4 (Web Text))

Max Activating Token Index: 15

Text #9

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0287. Min Act: -0.0000

Data Index: 1377391 (Python Code)

Max Activating Token Index: 850

Text #10

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0272. Min Act: -0.0000

Data Index: 1208720 (C4 (Web Text))

Max Activating Token Index: 753

Text #11

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0260. Min Act: -0.0000

Data Index: 345255 (C4 (Web Text))

Max Activating Token Index: 558

Text #12

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0271. Min Act: -0.0000

Data Index: 890201 (C4 (Web Text))

Max Activating Token Index: 434

Text #13

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0272. Min Act: -0.0000

Data Index: 214524 (C4 (Web Text))

Max Activating Token Index: 1010

Text #14

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0275. Min Act: -0.0000

Data Index: 50789 (C4 (Web Text))

Max Activating Token Index: 439

Text #15

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0229. Min Act: -0.0000

Data Index: 146146 (C4 (Web Text))

Max Activating Token Index: 221

Text #16

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0271. Min Act: -0.0000

Data Index: 1044487 (C4 (Web Text))

Max Activating Token Index: 873

Text #17

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0260. Min Act: -0.0000

Data Index: 992580 (C4 (Web Text))

Max Activating Token Index: 64

Text #18

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0234. Min Act: -0.0000

Data Index: 778224 (C4 (Web Text))

Max Activating Token Index: 191

Text #19

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0257. Min Act: -0.0000

Data Index: 1607441 (Python Code)

Max Activating Token Index: 870