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

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

Neuron 4341 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.7111. Min Range: -4.7111

Max Act: 4.7111. Min Act: -0.0001

Data Index: 1151351 (C4 (Web Text))

Max Activating Token Index: 432

Text #1

Max Range: 4.7111. Min Range: -4.7111

Max Act: 4.4382. Min Act: -0.0000

Data Index: 865551 (C4 (Web Text))

Max Activating Token Index: 718

Text #2

Max Range: 4.7111. Min Range: -4.7111

Max Act: 4.4086. Min Act: -0.0000

Data Index: 939242 (C4 (Web Text))

Max Activating Token Index: 102

Text #3

Max Range: 4.7111. Min Range: -4.7111

Max Act: 3.4949. Min Act: -0.0000

Data Index: 1195415 (C4 (Web Text))

Max Activating Token Index: 316

Text #4

Max Range: 4.7111. Min Range: -4.7111

Max Act: 4.3933. Min Act: -0.0000

Data Index: 1146986 (C4 (Web Text))

Max Activating Token Index: 916

Text #5

Max Range: 4.7111. Min Range: -4.7111

Max Act: 4.0648. Min Act: -0.0000

Data Index: 105600 (C4 (Web Text))

Max Activating Token Index: 44

Text #6

Max Range: 4.7111. Min Range: -4.7111

Max Act: 3.8214. Min Act: -0.0001

Data Index: 55977 (C4 (Web Text))

Max Activating Token Index: 775

Text #7

Max Range: 4.7111. Min Range: -4.7111

Max Act: 3.7300. Min Act: -0.0000

Data Index: 666602 (C4 (Web Text))

Max Activating Token Index: 147

Text #8

Max Range: 4.7111. Min Range: -4.7111

Max Act: 3.5422. Min Act: -0.0000

Data Index: 133508 (C4 (Web Text))

Max Activating Token Index: 31

Text #9

Max Range: 4.7111. Min Range: -4.7111

Max Act: 3.5756. Min Act: -0.0000

Data Index: 284711 (C4 (Web Text))

Max Activating Token Index: 119

Text #10

Max Range: 4.7111. Min Range: -4.7111

Max Act: 3.4111. Min Act: -0.0000

Data Index: 921973 (C4 (Web Text))

Max Activating Token Index: 523

Text #11

Max Range: 4.7111. Min Range: -4.7111

Max Act: 3.5376. Min Act: -0.0000

Data Index: 405216 (C4 (Web Text))

Max Activating Token Index: 52

Text #12

Max Range: 4.7111. Min Range: -4.7111

Max Act: 3.2497. Min Act: -0.0000

Data Index: 421167 (C4 (Web Text))

Max Activating Token Index: 703

Text #13

Max Range: 4.7111. Min Range: -4.7111

Max Act: 3.3624. Min Act: -0.0000

Data Index: 394182 (C4 (Web Text))

Max Activating Token Index: 421

Text #14

Max Range: 4.7111. Min Range: -4.7111

Max Act: 3.2184. Min Act: -0.0000

Data Index: 438893 (C4 (Web Text))

Max Activating Token Index: 650

Text #15

Max Range: 4.7111. Min Range: -4.7111

Max Act: 3.2192. Min Act: -0.0000

Data Index: 564960 (C4 (Web Text))

Max Activating Token Index: 278

Text #16

Max Range: 4.7111. Min Range: -4.7111

Max Act: 2.9306. Min Act: -0.0000

Data Index: 511600 (C4 (Web Text))

Max Activating Token Index: 229

Text #17

Max Range: 4.7111. Min Range: -4.7111

Max Act: 3.2171. Min Act: -0.0000

Data Index: 206013 (C4 (Web Text))

Max Activating Token Index: 620

Text #18

Max Range: 4.7111. Min Range: -4.7111

Max Act: 3.1970. Min Act: -0.0000

Data Index: 776204 (C4 (Web Text))

Max Activating Token Index: 430

Text #19

Max Range: 4.7111. Min Range: -4.7111

Max Act: 3.3361. Min Act: -0.0000

Data Index: 1307659 (C4 (Web Text))

Max Activating Token Index: 182