Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2646 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1220. Min Range: -0.1220

Max Act: 0.1220. Min Act: -0.0003

Data Index: 75234 (C4 (Web Text))

Max Activating Token Index: 98

Text #1

Max Range: 0.1220. Min Range: -0.1220

Max Act: 0.0943. Min Act: -0.0003

Data Index: 1001676 (C4 (Web Text))

Max Activating Token Index: 894

Text #2

Max Range: 0.1220. Min Range: -0.1220

Max Act: 0.0701. Min Act: -0.0003

Data Index: 1267873 (C4 (Web Text))

Max Activating Token Index: 568

Text #3

Max Range: 0.1220. Min Range: -0.1220

Max Act: 0.0656. Min Act: -0.0003

Data Index: 818290 (C4 (Web Text))

Max Activating Token Index: 864

Text #4

Max Range: 0.1220. Min Range: -0.1220

Max Act: 0.0808. Min Act: -0.0003

Data Index: 1137074 (C4 (Web Text))

Max Activating Token Index: 975

Text #5

Max Range: 0.1220. Min Range: -0.1220

Max Act: 0.0740. Min Act: -0.0003

Data Index: 197106 (C4 (Web Text))

Max Activating Token Index: 876

Text #6

Max Range: 0.1220. Min Range: -0.1220

Max Act: 0.0698. Min Act: -0.0003

Data Index: 31072 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.1220. Min Range: -0.1220

Max Act: 0.0736. Min Act: -0.0003

Data Index: 300859 (C4 (Web Text))

Max Activating Token Index: 800

Text #8

Max Range: 0.1220. Min Range: -0.1220

Max Act: 0.0702. Min Act: -0.0003

Data Index: 1050527 (C4 (Web Text))

Max Activating Token Index: 712

Text #9

Max Range: 0.1220. Min Range: -0.1220

Max Act: 0.0531. Min Act: -0.0003

Data Index: 1013956 (C4 (Web Text))

Max Activating Token Index: 838

Text #10

Max Range: 0.1220. Min Range: -0.1220

Max Act: 0.0850. Min Act: -0.0003

Data Index: 1087520 (C4 (Web Text))

Max Activating Token Index: 940

Text #11

Max Range: 0.1220. Min Range: -0.1220

Max Act: 0.0708. Min Act: -0.0003

Data Index: 700855 (C4 (Web Text))

Max Activating Token Index: 859

Text #12

Max Range: 0.1220. Min Range: -0.1220

Max Act: 0.0715. Min Act: -0.0003

Data Index: 341531 (C4 (Web Text))

Max Activating Token Index: 603

Text #13

Max Range: 0.1220. Min Range: -0.1220

Max Act: 0.0604. Min Act: -0.0003

Data Index: 321845 (C4 (Web Text))

Max Activating Token Index: 912

Text #14

Max Range: 0.1220. Min Range: -0.1220

Max Act: 0.0784. Min Act: -0.0003

Data Index: 712603 (C4 (Web Text))

Max Activating Token Index: 157

Text #15

Max Range: 0.1220. Min Range: -0.1220

Max Act: 0.0700. Min Act: -0.0003

Data Index: 451361 (C4 (Web Text))

Max Activating Token Index: 148

Text #16

Max Range: 0.1220. Min Range: -0.1220

Max Act: 0.0700. Min Act: -0.0003

Data Index: 266144 (C4 (Web Text))

Max Activating Token Index: 146

Text #17

Max Range: 0.1220. Min Range: -0.1220

Max Act: 0.0657. Min Act: -0.0003

Data Index: 1119245 (C4 (Web Text))

Max Activating Token Index: 533

Text #18

Max Range: 0.1220. Min Range: -0.1220

Max Act: 0.0796. Min Act: -0.0003

Data Index: 420956 (C4 (Web Text))

Max Activating Token Index: 190

Text #19

Max Range: 0.1220. Min Range: -0.1220

Max Act: 0.0772. Min Act: -0.0003

Data Index: 433281 (C4 (Web Text))

Max Activating Token Index: 704