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

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

Neuron 4902 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9179. Min Range: -1.9179

Max Act: 1.9179. Min Act: -0.0001

Data Index: 682176 (C4 (Web Text))

Max Activating Token Index: 149

Text #1

Max Range: 1.9179. Min Range: -1.9179

Max Act: 1.6412. Min Act: -0.0001

Data Index: 955103 (C4 (Web Text))

Max Activating Token Index: 235

Text #2

Max Range: 1.9179. Min Range: -1.9179

Max Act: 1.6703. Min Act: -0.0001

Data Index: 626368 (C4 (Web Text))

Max Activating Token Index: 500

Text #3

Max Range: 1.9179. Min Range: -1.9179

Max Act: 1.5129. Min Act: -0.0001

Data Index: 325105 (C4 (Web Text))

Max Activating Token Index: 327

Text #4

Max Range: 1.9179. Min Range: -1.9179

Max Act: 1.5191. Min Act: -0.0001

Data Index: 93838 (C4 (Web Text))

Max Activating Token Index: 315

Text #5

Max Range: 1.9179. Min Range: -1.9179

Max Act: 1.5584. Min Act: -0.0001

Data Index: 449956 (C4 (Web Text))

Max Activating Token Index: 79

Text #6

Max Range: 1.9179. Min Range: -1.9179

Max Act: 1.4382. Min Act: -0.0001

Data Index: 1318677 (C4 (Web Text))

Max Activating Token Index: 398

Text #7

Max Range: 1.9179. Min Range: -1.9179

Max Act: 1.3617. Min Act: -0.0001

Data Index: 402180 (C4 (Web Text))

Max Activating Token Index: 424

Text #8

Max Range: 1.9179. Min Range: -1.9179

Max Act: 1.3156. Min Act: -0.0001

Data Index: 213390 (C4 (Web Text))

Max Activating Token Index: 383

Text #9

Max Range: 1.9179. Min Range: -1.9179

Max Act: 1.3519. Min Act: -0.0001

Data Index: 291852 (C4 (Web Text))

Max Activating Token Index: 516

Text #10

Max Range: 1.9179. Min Range: -1.9179

Max Act: 1.3792. Min Act: -0.0001

Data Index: 1113996 (C4 (Web Text))

Max Activating Token Index: 423

Text #11

Max Range: 1.9179. Min Range: -1.9179

Max Act: 1.3267. Min Act: -0.0001

Data Index: 1179719 (C4 (Web Text))

Max Activating Token Index: 518

Text #12

Max Range: 1.9179. Min Range: -1.9179

Max Act: 1.3172. Min Act: -0.0001

Data Index: 724939 (C4 (Web Text))

Max Activating Token Index: 682

Text #13

Max Range: 1.9179. Min Range: -1.9179

Max Act: 1.3334. Min Act: -0.0001

Data Index: 1489339 (Python Code)

Max Activating Token Index: 67

Text #14

Max Range: 1.9179. Min Range: -1.9179

Max Act: 1.2973. Min Act: -0.0001

Data Index: 1403505 (Python Code)

Max Activating Token Index: 922

Text #15

Max Range: 1.9179. Min Range: -1.9179

Max Act: 1.3058. Min Act: -0.0001

Data Index: 939894 (C4 (Web Text))

Max Activating Token Index: 853

Text #16

Max Range: 1.9179. Min Range: -1.9179

Max Act: 1.2571. Min Act: -0.0001

Data Index: 411424 (C4 (Web Text))

Max Activating Token Index: 152

Text #17

Max Range: 1.9179. Min Range: -1.9179

Max Act: 1.3229. Min Act: -0.0001

Data Index: 1502510 (Python Code)

Max Activating Token Index: 69

Text #18

Max Range: 1.9179. Min Range: -1.9179

Max Act: 1.2826. Min Act: -0.0001

Data Index: 1307733 (C4 (Web Text))

Max Activating Token Index: 780

Text #19

Max Range: 1.9179. Min Range: -1.9179

Max Act: 1.2442. Min Act: -0.0001

Data Index: 1025891 (C4 (Web Text))

Max Activating Token Index: 545