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

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

Neuron 959 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5727. Min Range: -1.5727

Max Act: 1.5727. Min Act: -0.0000

Data Index: 1495927 (Python Code)

Max Activating Token Index: 770

Text #1

Max Range: 1.5727. Min Range: -1.5727

Max Act: 1.4929. Min Act: -0.0000

Data Index: 79997 (C4 (Web Text))

Max Activating Token Index: 324

Text #2

Max Range: 1.5727. Min Range: -1.5727

Max Act: 1.5382. Min Act: -0.0000

Data Index: 316917 (C4 (Web Text))

Max Activating Token Index: 190

Text #3

Max Range: 1.5727. Min Range: -1.5727

Max Act: 1.2611. Min Act: -0.0000

Data Index: 882146 (C4 (Web Text))

Max Activating Token Index: 828

Text #4

Max Range: 1.5727. Min Range: -1.5727

Max Act: 1.3725. Min Act: -0.0000

Data Index: 158037 (C4 (Web Text))

Max Activating Token Index: 504

Text #5

Max Range: 1.5727. Min Range: -1.5727

Max Act: 1.3669. Min Act: -0.0000

Data Index: 176453 (C4 (Web Text))

Max Activating Token Index: 686

Text #6

Max Range: 1.5727. Min Range: -1.5727

Max Act: 1.2489. Min Act: -0.0000

Data Index: 1592500 (Python Code)

Max Activating Token Index: 45

Text #7

Max Range: 1.5727. Min Range: -1.5727

Max Act: 1.2361. Min Act: -0.0000

Data Index: 1559836 (Python Code)

Max Activating Token Index: 410

Text #8

Max Range: 1.5727. Min Range: -1.5727

Max Act: 1.2356. Min Act: -0.0000

Data Index: 270648 (C4 (Web Text))

Max Activating Token Index: 55

Text #9

Max Range: 1.5727. Min Range: -1.5727

Max Act: 1.2180. Min Act: -0.0000

Data Index: 1040545 (C4 (Web Text))

Max Activating Token Index: 692

Text #10

Max Range: 1.5727. Min Range: -1.5727

Max Act: 1.1889. Min Act: -0.0000

Data Index: 1115765 (C4 (Web Text))

Max Activating Token Index: 433

Text #11

Max Range: 1.5727. Min Range: -1.5727

Max Act: 1.1250. Min Act: -0.0000

Data Index: 92360 (C4 (Web Text))

Max Activating Token Index: 125

Text #12

Max Range: 1.5727. Min Range: -1.5727

Max Act: 1.1767. Min Act: -0.0000

Data Index: 199464 (C4 (Web Text))

Max Activating Token Index: 595

Text #13

Max Range: 1.5727. Min Range: -1.5727

Max Act: 1.2543. Min Act: -0.0000

Data Index: 882149 (C4 (Web Text))

Max Activating Token Index: 206

Text #14

Max Range: 1.5727. Min Range: -1.5727

Max Act: 1.1435. Min Act: -0.0000

Data Index: 1107064 (C4 (Web Text))

Max Activating Token Index: 205

Text #15

Max Range: 1.5727. Min Range: -1.5727

Max Act: 1.2052. Min Act: -0.0000

Data Index: 165985 (C4 (Web Text))

Max Activating Token Index: 612

Text #16

Max Range: 1.5727. Min Range: -1.5727

Max Act: 1.1212. Min Act: -0.0000

Data Index: 1033026 (C4 (Web Text))

Max Activating Token Index: 345

Text #17

Max Range: 1.5727. Min Range: -1.5727

Max Act: 1.1090. Min Act: -0.0000

Data Index: 119731 (C4 (Web Text))

Max Activating Token Index: 479

Text #18

Max Range: 1.5727. Min Range: -1.5727

Max Act: 1.1045. Min Act: -0.0000

Data Index: 709725 (C4 (Web Text))

Max Activating Token Index: 271

Text #19

Max Range: 1.5727. Min Range: -1.5727

Max Act: 0.9852. Min Act: -0.0000

Data Index: 990356 (C4 (Web Text))

Max Activating Token Index: 799