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

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

Neuron 4041 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.7844. Min Range: -4.7844

Max Act: 4.7844. Min Act: -0.0000

Data Index: 531138 (C4 (Web Text))

Max Activating Token Index: 942

Text #1

Max Range: 4.7844. Min Range: -4.7844

Max Act: 3.6344. Min Act: -0.0000

Data Index: 250296 (C4 (Web Text))

Max Activating Token Index: 817

Text #2

Max Range: 4.7844. Min Range: -4.7844

Max Act: 3.5827. Min Act: -0.0000

Data Index: 1240815 (C4 (Web Text))

Max Activating Token Index: 155

Text #3

Max Range: 4.7844. Min Range: -4.7844

Max Act: 3.6675. Min Act: -0.0000

Data Index: 862898 (C4 (Web Text))

Max Activating Token Index: 42

Text #4

Max Range: 4.7844. Min Range: -4.7844

Max Act: 3.6883. Min Act: -0.0000

Data Index: 948008 (C4 (Web Text))

Max Activating Token Index: 927

Text #5

Max Range: 4.7844. Min Range: -4.7844

Max Act: 3.6625. Min Act: -0.0000

Data Index: 1322646 (C4 (Web Text))

Max Activating Token Index: 198

Text #6

Max Range: 4.7844. Min Range: -4.7844

Max Act: 3.6095. Min Act: -0.0000

Data Index: 669622 (C4 (Web Text))

Max Activating Token Index: 588

Text #7

Max Range: 4.7844. Min Range: -4.7844

Max Act: 3.4447. Min Act: -0.0000

Data Index: 1075542 (C4 (Web Text))

Max Activating Token Index: 298

Text #8

Max Range: 4.7844. Min Range: -4.7844

Max Act: 3.5907. Min Act: -0.0000

Data Index: 431556 (C4 (Web Text))

Max Activating Token Index: 239

Text #9

Max Range: 4.7844. Min Range: -4.7844

Max Act: 3.3909. Min Act: -0.0000

Data Index: 639097 (C4 (Web Text))

Max Activating Token Index: 931

Text #10

Max Range: 4.7844. Min Range: -4.7844

Max Act: 3.5219. Min Act: -0.0000

Data Index: 1137924 (C4 (Web Text))

Max Activating Token Index: 539

Text #11

Max Range: 4.7844. Min Range: -4.7844

Max Act: 3.4831. Min Act: -0.0000

Data Index: 888165 (C4 (Web Text))

Max Activating Token Index: 520

Text #12

Max Range: 4.7844. Min Range: -4.7844

Max Act: 3.4673. Min Act: -0.0000

Data Index: 835205 (C4 (Web Text))

Max Activating Token Index: 585

Text #13

Max Range: 4.7844. Min Range: -4.7844

Max Act: 3.4550. Min Act: -0.0000

Data Index: 442919 (C4 (Web Text))

Max Activating Token Index: 172

Text #14

Max Range: 4.7844. Min Range: -4.7844

Max Act: 3.4350. Min Act: -0.0000

Data Index: 591354 (C4 (Web Text))

Max Activating Token Index: 580

Text #15

Max Range: 4.7844. Min Range: -4.7844

Max Act: 3.2149. Min Act: -0.0000

Data Index: 292854 (C4 (Web Text))

Max Activating Token Index: 265

Text #16

Max Range: 4.7844. Min Range: -4.7844

Max Act: 3.3386. Min Act: -0.0000

Data Index: 5282 (C4 (Web Text))

Max Activating Token Index: 858

Text #17

Max Range: 4.7844. Min Range: -4.7844

Max Act: 3.3374. Min Act: -0.0000

Data Index: 1015363 (C4 (Web Text))

Max Activating Token Index: 411

Text #18

Max Range: 4.7844. Min Range: -4.7844

Max Act: 3.3013. Min Act: -0.0000

Data Index: 236564 (C4 (Web Text))

Max Activating Token Index: 1001

Text #19

Max Range: 4.7844. Min Range: -4.7844

Max Act: 3.3208. Min Act: -0.0000

Data Index: 1008241 (C4 (Web Text))

Max Activating Token Index: 286