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

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

Neuron 2433 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5002. Min Range: -1.5002

Max Act: 1.4210. Min Act: -0.0000

Data Index: 1261188 (C4 (Web Text))

Max Activating Token Index: 262

Text #1

Max Range: 1.5002. Min Range: -1.5002

Max Act: 1.5002. Min Act: -0.0000

Data Index: 40931 (C4 (Web Text))

Max Activating Token Index: 89

Text #2

Max Range: 1.5002. Min Range: -1.5002

Max Act: 1.4787. Min Act: -0.0000

Data Index: 690935 (C4 (Web Text))

Max Activating Token Index: 607

Text #3

Max Range: 1.5002. Min Range: -1.5002

Max Act: 1.4614. Min Act: -0.0000

Data Index: 561846 (C4 (Web Text))

Max Activating Token Index: 467

Text #4

Max Range: 1.5002. Min Range: -1.5002

Max Act: 1.3854. Min Act: -0.0000

Data Index: 203139 (C4 (Web Text))

Max Activating Token Index: 165

Text #5

Max Range: 1.5002. Min Range: -1.5002

Max Act: 1.4187. Min Act: -0.0000

Data Index: 933809 (C4 (Web Text))

Max Activating Token Index: 861

Text #6

Max Range: 1.5002. Min Range: -1.5002

Max Act: 1.3872. Min Act: -0.0000

Data Index: 949658 (C4 (Web Text))

Max Activating Token Index: 682

Text #7

Max Range: 1.5002. Min Range: -1.5002

Max Act: 1.3637. Min Act: -0.0000

Data Index: 626891 (C4 (Web Text))

Max Activating Token Index: 589

Text #8

Max Range: 1.5002. Min Range: -1.5002

Max Act: 1.3680. Min Act: -0.0000

Data Index: 774112 (C4 (Web Text))

Max Activating Token Index: 216

Text #9

Max Range: 1.5002. Min Range: -1.5002

Max Act: 1.3400. Min Act: -0.0000

Data Index: 107563 (C4 (Web Text))

Max Activating Token Index: 263

Text #10

Max Range: 1.5002. Min Range: -1.5002

Max Act: 1.3145. Min Act: -0.0000

Data Index: 1237015 (C4 (Web Text))

Max Activating Token Index: 40

Text #11

Max Range: 1.5002. Min Range: -1.5002

Max Act: 1.2568. Min Act: -0.0000

Data Index: 30013 (C4 (Web Text))

Max Activating Token Index: 198

Text #12

Max Range: 1.5002. Min Range: -1.5002

Max Act: 1.2542. Min Act: 0.0000

Data Index: 858577 (C4 (Web Text))

Max Activating Token Index: 301

Text #13

Max Range: 1.5002. Min Range: -1.5002

Max Act: 1.1731. Min Act: -0.0000

Data Index: 785132 (C4 (Web Text))

Max Activating Token Index: 726

Text #14

Max Range: 1.5002. Min Range: -1.5002

Max Act: 1.2134. Min Act: -0.0000

Data Index: 940677 (C4 (Web Text))

Max Activating Token Index: 573

Text #15

Max Range: 1.5002. Min Range: -1.5002

Max Act: 1.2073. Min Act: -0.0000

Data Index: 725277 (C4 (Web Text))

Max Activating Token Index: 159

Text #16

Max Range: 1.5002. Min Range: -1.5002

Max Act: 1.1986. Min Act: -0.0000

Data Index: 948512 (C4 (Web Text))

Max Activating Token Index: 73

Text #17

Max Range: 1.5002. Min Range: -1.5002

Max Act: 1.1945. Min Act: -0.0000

Data Index: 733709 (C4 (Web Text))

Max Activating Token Index: 138

Text #18

Max Range: 1.5002. Min Range: -1.5002

Max Act: 1.1974. Min Act: -0.0000

Data Index: 725801 (C4 (Web Text))

Max Activating Token Index: 98

Text #19

Max Range: 1.5002. Min Range: -1.5002

Max Act: 1.1946. Min Act: -0.0000

Data Index: 661568 (C4 (Web Text))

Max Activating Token Index: 318