Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1991 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3316. Min Range: -0.3316

Max Act: 0.3316. Min Act: -0.0000

Data Index: 1279003 (C4 (Web Text))

Max Activating Token Index: 583

Text #1

Max Range: 0.3316. Min Range: -0.3316

Max Act: 0.3065. Min Act: -0.0000

Data Index: 1066864 (C4 (Web Text))

Max Activating Token Index: 659

Text #2

Max Range: 0.3316. Min Range: -0.3316

Max Act: 0.2867. Min Act: -0.0001

Data Index: 229824 (C4 (Web Text))

Max Activating Token Index: 209

Text #3

Max Range: 0.3316. Min Range: -0.3316

Max Act: 0.2865. Min Act: -0.0000

Data Index: 1112585 (C4 (Web Text))

Max Activating Token Index: 401

Text #4

Max Range: 0.3316. Min Range: -0.3316

Max Act: 0.2837. Min Act: -0.0000

Data Index: 341237 (C4 (Web Text))

Max Activating Token Index: 872

Text #5

Max Range: 0.3316. Min Range: -0.3316

Max Act: 0.2557. Min Act: -0.0000

Data Index: 926986 (C4 (Web Text))

Max Activating Token Index: 504

Text #6

Max Range: 0.3316. Min Range: -0.3316

Max Act: 0.2619. Min Act: -0.0001

Data Index: 607520 (C4 (Web Text))

Max Activating Token Index: 922

Text #7

Max Range: 0.3316. Min Range: -0.3316

Max Act: 0.2597. Min Act: -0.0000

Data Index: 438587 (C4 (Web Text))

Max Activating Token Index: 395

Text #8

Max Range: 0.3316. Min Range: -0.3316

Max Act: 0.2488. Min Act: -0.0000

Data Index: 640934 (C4 (Web Text))

Max Activating Token Index: 799

Text #9

Max Range: 0.3316. Min Range: -0.3316

Max Act: 0.2420. Min Act: -0.0001

Data Index: 990358 (C4 (Web Text))

Max Activating Token Index: 836

Text #10

Max Range: 0.3316. Min Range: -0.3316

Max Act: 0.2368. Min Act: -0.0000

Data Index: 435692 (C4 (Web Text))

Max Activating Token Index: 63

Text #11

Max Range: 0.3316. Min Range: -0.3316

Max Act: 0.2285. Min Act: -0.0000

Data Index: 371807 (C4 (Web Text))

Max Activating Token Index: 245

Text #12

Max Range: 0.3316. Min Range: -0.3316

Max Act: 0.2300. Min Act: -0.0000

Data Index: 476477 (C4 (Web Text))

Max Activating Token Index: 680

Text #13

Max Range: 0.3316. Min Range: -0.3316

Max Act: 0.2336. Min Act: -0.0001

Data Index: 1033335 (C4 (Web Text))

Max Activating Token Index: 253

Text #14

Max Range: 0.3316. Min Range: -0.3316

Max Act: 0.2371. Min Act: -0.0000

Data Index: 836811 (C4 (Web Text))

Max Activating Token Index: 195

Text #15

Max Range: 0.3316. Min Range: -0.3316

Max Act: 0.2258. Min Act: -0.0001

Data Index: 232385 (C4 (Web Text))

Max Activating Token Index: 1014

Text #16

Max Range: 0.3316. Min Range: -0.3316

Max Act: 0.2279. Min Act: -0.0000

Data Index: 106800 (C4 (Web Text))

Max Activating Token Index: 233

Text #17

Max Range: 0.3316. Min Range: -0.3316

Max Act: 0.2171. Min Act: -0.0000

Data Index: 1130515 (C4 (Web Text))

Max Activating Token Index: 570

Text #18

Max Range: 0.3316. Min Range: -0.3316

Max Act: 0.2231. Min Act: -0.0000

Data Index: 220075 (C4 (Web Text))

Max Activating Token Index: 401

Text #19

Max Range: 0.3316. Min Range: -0.3316

Max Act: 0.2191. Min Act: -0.0001

Data Index: 945673 (C4 (Web Text))

Max Activating Token Index: 266