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

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

Neuron 2327 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1356. Min Range: -0.1356

Max Act: 0.1356. Min Act: -0.0003

Data Index: 1161422 (C4 (Web Text))

Max Activating Token Index: 329

Text #1

Max Range: 0.1356. Min Range: -0.1356

Max Act: 0.1320. Min Act: -0.0003

Data Index: 99798 (C4 (Web Text))

Max Activating Token Index: 494

Text #2

Max Range: 0.1356. Min Range: -0.1356

Max Act: 0.1131. Min Act: -0.0002

Data Index: 148268 (C4 (Web Text))

Max Activating Token Index: 30

Text #3

Max Range: 0.1356. Min Range: -0.1356

Max Act: 0.1140. Min Act: -0.0002

Data Index: 476100 (C4 (Web Text))

Max Activating Token Index: 580

Text #4

Max Range: 0.1356. Min Range: -0.1356

Max Act: 0.1000. Min Act: -0.0003

Data Index: 1322725 (C4 (Web Text))

Max Activating Token Index: 486

Text #5

Max Range: 0.1356. Min Range: -0.1356

Max Act: 0.1019. Min Act: -0.0003

Data Index: 221957 (C4 (Web Text))

Max Activating Token Index: 580

Text #6

Max Range: 0.1356. Min Range: -0.1356

Max Act: 0.1013. Min Act: -0.0003

Data Index: 1140809 (C4 (Web Text))

Max Activating Token Index: 25

Text #7

Max Range: 0.1356. Min Range: -0.1356

Max Act: 0.0959. Min Act: -0.0003

Data Index: 910932 (C4 (Web Text))

Max Activating Token Index: 5

Text #8

Max Range: 0.1356. Min Range: -0.1356

Max Act: 0.1028. Min Act: -0.0002

Data Index: 211380 (C4 (Web Text))

Max Activating Token Index: 761

Text #9

Max Range: 0.1356. Min Range: -0.1356

Max Act: 0.0981. Min Act: -0.0003

Data Index: 298669 (C4 (Web Text))

Max Activating Token Index: 716

Text #10

Max Range: 0.1356. Min Range: -0.1356

Max Act: 0.0931. Min Act: -0.0002

Data Index: 569223 (C4 (Web Text))

Max Activating Token Index: 315

Text #11

Max Range: 0.1356. Min Range: -0.1356

Max Act: 0.0959. Min Act: -0.0003

Data Index: 1286196 (C4 (Web Text))

Max Activating Token Index: 664

Text #12

Max Range: 0.1356. Min Range: -0.1356

Max Act: 0.0879. Min Act: -0.0003

Data Index: 693175 (C4 (Web Text))

Max Activating Token Index: 676

Text #13

Max Range: 0.1356. Min Range: -0.1356

Max Act: 0.0948. Min Act: -0.0003

Data Index: 1153697 (C4 (Web Text))

Max Activating Token Index: 23

Text #14

Max Range: 0.1356. Min Range: -0.1356

Max Act: 0.0946. Min Act: -0.0003

Data Index: 238933 (C4 (Web Text))

Max Activating Token Index: 753

Text #15

Max Range: 0.1356. Min Range: -0.1356

Max Act: 0.0940. Min Act: -0.0003

Data Index: 441784 (C4 (Web Text))

Max Activating Token Index: 447

Text #16

Max Range: 0.1356. Min Range: -0.1356

Max Act: 0.0935. Min Act: -0.0003

Data Index: 306074 (C4 (Web Text))

Max Activating Token Index: 686

Text #17

Max Range: 0.1356. Min Range: -0.1356

Max Act: 0.0961. Min Act: -0.0003

Data Index: 1082655 (C4 (Web Text))

Max Activating Token Index: 761

Text #18

Max Range: 0.1356. Min Range: -0.1356

Max Act: 0.0926. Min Act: -0.0003

Data Index: 312964 (C4 (Web Text))

Max Activating Token Index: 345

Text #19

Max Range: 0.1356. Min Range: -0.1356

Max Act: 0.0956. Min Act: -0.0003

Data Index: 517240 (C4 (Web Text))

Max Activating Token Index: 214