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

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

Neuron 5076 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8002. Min Range: -1.8002

Max Act: 1.8002. Min Act: -0.0001

Data Index: 547465 (C4 (Web Text))

Max Activating Token Index: 225

Text #1

Max Range: 1.8002. Min Range: -1.8002

Max Act: 1.7134. Min Act: -0.0001

Data Index: 131263 (C4 (Web Text))

Max Activating Token Index: 489

Text #2

Max Range: 1.8002. Min Range: -1.8002

Max Act: 1.6729. Min Act: -0.0001

Data Index: 1308932 (C4 (Web Text))

Max Activating Token Index: 8

Text #3

Max Range: 1.8002. Min Range: -1.8002

Max Act: 1.5447. Min Act: -0.0001

Data Index: 588681 (C4 (Web Text))

Max Activating Token Index: 832

Text #4

Max Range: 1.8002. Min Range: -1.8002

Max Act: 1.6359. Min Act: -0.0001

Data Index: 398529 (C4 (Web Text))

Max Activating Token Index: 60

Text #5

Max Range: 1.8002. Min Range: -1.8002

Max Act: 1.5556. Min Act: -0.0001

Data Index: 1057639 (C4 (Web Text))

Max Activating Token Index: 502

Text #6

Max Range: 1.8002. Min Range: -1.8002

Max Act: 1.5924. Min Act: -0.0001

Data Index: 250053 (C4 (Web Text))

Max Activating Token Index: 562

Text #7

Max Range: 1.8002. Min Range: -1.8002

Max Act: 1.5914. Min Act: -0.0001

Data Index: 821645 (C4 (Web Text))

Max Activating Token Index: 318

Text #8

Max Range: 1.8002. Min Range: -1.8002

Max Act: 1.4381. Min Act: -0.0001

Data Index: 322953 (C4 (Web Text))

Max Activating Token Index: 522

Text #9

Max Range: 1.8002. Min Range: -1.8002

Max Act: 1.5060. Min Act: -0.0001

Data Index: 672579 (C4 (Web Text))

Max Activating Token Index: 281

Text #10

Max Range: 1.8002. Min Range: -1.8002

Max Act: 1.4679. Min Act: -0.0001

Data Index: 781434 (C4 (Web Text))

Max Activating Token Index: 596

Text #11

Max Range: 1.8002. Min Range: -1.8002

Max Act: 1.5318. Min Act: -0.0001

Data Index: 547309 (C4 (Web Text))

Max Activating Token Index: 859

Text #12

Max Range: 1.8002. Min Range: -1.8002

Max Act: 1.5399. Min Act: -0.0001

Data Index: 65857 (C4 (Web Text))

Max Activating Token Index: 603

Text #13

Max Range: 1.8002. Min Range: -1.8002

Max Act: 1.4254. Min Act: -0.0001

Data Index: 373346 (C4 (Web Text))

Max Activating Token Index: 91

Text #14

Max Range: 1.8002. Min Range: -1.8002

Max Act: 1.3392. Min Act: -0.0001

Data Index: 388830 (C4 (Web Text))

Max Activating Token Index: 155

Text #15

Max Range: 1.8002. Min Range: -1.8002

Max Act: 1.4180. Min Act: -0.0001

Data Index: 1218767 (C4 (Web Text))

Max Activating Token Index: 118

Text #16

Max Range: 1.8002. Min Range: -1.8002

Max Act: 1.2981. Min Act: -0.0001

Data Index: 846259 (C4 (Web Text))

Max Activating Token Index: 709

Text #17

Max Range: 1.8002. Min Range: -1.8002

Max Act: 1.3537. Min Act: -0.0001

Data Index: 1030225 (C4 (Web Text))

Max Activating Token Index: 935

Text #18

Max Range: 1.8002. Min Range: -1.8002

Max Act: 1.3808. Min Act: -0.0001

Data Index: 1033867 (C4 (Web Text))

Max Activating Token Index: 3

Text #19

Max Range: 1.8002. Min Range: -1.8002

Max Act: 1.3345. Min Act: -0.0001

Data Index: 1097995 (C4 (Web Text))

Max Activating Token Index: 966