Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1206 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 3.8906. Min Range: -3.8906

Max Act: 3.8906. Min Act: -0.0000

Data Index: 1312650 (C4 (Web Text))

Max Activating Token Index: 716

Text #1

Max Range: 3.8906. Min Range: -3.8906

Max Act: 3.5152. Min Act: 0.0001

Data Index: 1292020 (C4 (Web Text))

Max Activating Token Index: 536

Text #2

Max Range: 3.8906. Min Range: -3.8906

Max Act: 3.1129. Min Act: 0.0000

Data Index: 674084 (C4 (Web Text))

Max Activating Token Index: 30

Text #3

Max Range: 3.8906. Min Range: -3.8906

Max Act: 2.9616. Min Act: 0.0000

Data Index: 934293 (C4 (Web Text))

Max Activating Token Index: 125

Text #4

Max Range: 3.8906. Min Range: -3.8906

Max Act: 2.8816. Min Act: 0.0000

Data Index: 1185367 (C4 (Web Text))

Max Activating Token Index: 279

Text #5

Max Range: 3.8906. Min Range: -3.8906

Max Act: 2.7299. Min Act: -0.0000

Data Index: 124615 (C4 (Web Text))

Max Activating Token Index: 380

Text #6

Max Range: 3.8906. Min Range: -3.8906

Max Act: 2.9878. Min Act: 0.0001

Data Index: 249704 (C4 (Web Text))

Max Activating Token Index: 380

Text #7

Max Range: 3.8906. Min Range: -3.8906

Max Act: 2.4011. Min Act: -0.0000

Data Index: 194022 (C4 (Web Text))

Max Activating Token Index: 616

Text #8

Max Range: 3.8906. Min Range: -3.8906

Max Act: 2.3734. Min Act: -0.0000

Data Index: 623353 (C4 (Web Text))

Max Activating Token Index: 860

Text #9

Max Range: 3.8906. Min Range: -3.8906

Max Act: 2.3865. Min Act: -0.0000

Data Index: 290168 (C4 (Web Text))

Max Activating Token Index: 421

Text #10

Max Range: 3.8906. Min Range: -3.8906

Max Act: 2.5506. Min Act: -0.0000

Data Index: 142906 (C4 (Web Text))

Max Activating Token Index: 471

Text #11

Max Range: 3.8906. Min Range: -3.8906

Max Act: 2.4937. Min Act: -0.0000

Data Index: 761299 (C4 (Web Text))

Max Activating Token Index: 645

Text #12

Max Range: 3.8906. Min Range: -3.8906

Max Act: 2.8248. Min Act: -0.0001

Data Index: 171498 (C4 (Web Text))

Max Activating Token Index: 572

Text #13

Max Range: 3.8906. Min Range: -3.8906

Max Act: 2.4829. Min Act: -0.0000

Data Index: 269927 (C4 (Web Text))

Max Activating Token Index: 952

Text #14

Max Range: 3.8906. Min Range: -3.8906

Max Act: 1.8662. Min Act: -0.0000

Data Index: 418096 (C4 (Web Text))

Max Activating Token Index: 787

Text #15

Max Range: 3.8906. Min Range: -3.8906

Max Act: 2.4619. Min Act: -0.0000

Data Index: 102985 (C4 (Web Text))

Max Activating Token Index: 256

Text #16

Max Range: 3.8906. Min Range: -3.8906

Max Act: 2.5661. Min Act: -0.0000

Data Index: 733871 (C4 (Web Text))

Max Activating Token Index: 144

Text #17

Max Range: 3.8906. Min Range: -3.8906

Max Act: 2.2913. Min Act: -0.0000

Data Index: 881662 (C4 (Web Text))

Max Activating Token Index: 34

Text #18

Max Range: 3.8906. Min Range: -3.8906

Max Act: 2.4214. Min Act: -0.0000

Data Index: 340290 (C4 (Web Text))

Max Activating Token Index: 183

Text #19

Max Range: 3.8906. Min Range: -3.8906

Max Act: 2.3181. Min Act: -0.0000

Data Index: 247714 (C4 (Web Text))

Max Activating Token Index: 931