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

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

Neuron 3871 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: 0.5128. Min Range: -0.5128

Max Act: 0.5128. Min Act: -0.0000

Data Index: 414827 (C4 (Web Text))

Max Activating Token Index: 420

Text #1

Max Range: 0.5128. Min Range: -0.5128

Max Act: 0.4355. Min Act: -0.0000

Data Index: 438001 (C4 (Web Text))

Max Activating Token Index: 12

Text #2

Max Range: 0.5128. Min Range: -0.5128

Max Act: 0.3889. Min Act: -0.0000

Data Index: 813576 (C4 (Web Text))

Max Activating Token Index: 337

Text #3

Max Range: 0.5128. Min Range: -0.5128

Max Act: 0.3889. Min Act: -0.0000

Data Index: 971614 (C4 (Web Text))

Max Activating Token Index: 513

Text #4

Max Range: 0.5128. Min Range: -0.5128

Max Act: 0.3677. Min Act: -0.0000

Data Index: 47545 (C4 (Web Text))

Max Activating Token Index: 196

Text #5

Max Range: 0.5128. Min Range: -0.5128

Max Act: 0.3234. Min Act: -0.0000

Data Index: 805018 (C4 (Web Text))

Max Activating Token Index: 227

Text #6

Max Range: 0.5128. Min Range: -0.5128

Max Act: 0.2893. Min Act: -0.0000

Data Index: 2082 (C4 (Web Text))

Max Activating Token Index: 875

Text #7

Max Range: 0.5128. Min Range: -0.5128

Max Act: 0.2980. Min Act: -0.0000

Data Index: 592432 (C4 (Web Text))

Max Activating Token Index: 666

Text #8

Max Range: 0.5128. Min Range: -0.5128

Max Act: 0.3184. Min Act: -0.0000

Data Index: 385281 (C4 (Web Text))

Max Activating Token Index: 564

Text #9

Max Range: 0.5128. Min Range: -0.5128

Max Act: 0.3027. Min Act: -0.0000

Data Index: 650278 (C4 (Web Text))

Max Activating Token Index: 767

Text #10

Max Range: 0.5128. Min Range: -0.5128

Max Act: 0.2946. Min Act: -0.0000

Data Index: 551224 (C4 (Web Text))

Max Activating Token Index: 367

Text #11

Max Range: 0.5128. Min Range: -0.5128

Max Act: 0.3109. Min Act: -0.0000

Data Index: 675891 (C4 (Web Text))

Max Activating Token Index: 689

Text #12

Max Range: 0.5128. Min Range: -0.5128

Max Act: 0.2870. Min Act: -0.0000

Data Index: 805678 (C4 (Web Text))

Max Activating Token Index: 506

Text #13

Max Range: 0.5128. Min Range: -0.5128

Max Act: 0.2972. Min Act: -0.0000

Data Index: 238144 (C4 (Web Text))

Max Activating Token Index: 863

Text #14

Max Range: 0.5128. Min Range: -0.5128

Max Act: 0.2869. Min Act: -0.0000

Data Index: 696499 (C4 (Web Text))

Max Activating Token Index: 17

Text #15

Max Range: 0.5128. Min Range: -0.5128

Max Act: 0.2938. Min Act: -0.0000

Data Index: 152095 (C4 (Web Text))

Max Activating Token Index: 802

Text #16

Max Range: 0.5128. Min Range: -0.5128

Max Act: 0.2916. Min Act: -0.0000

Data Index: 866618 (C4 (Web Text))

Max Activating Token Index: 598

Text #17

Max Range: 0.5128. Min Range: -0.5128

Max Act: 0.2952. Min Act: -0.0000

Data Index: 47364 (C4 (Web Text))

Max Activating Token Index: 295

Text #18

Max Range: 0.5128. Min Range: -0.5128

Max Act: 0.2887. Min Act: -0.0000

Data Index: 1111227 (C4 (Web Text))

Max Activating Token Index: 720

Text #19

Max Range: 0.5128. Min Range: -0.5128

Max Act: 0.3086. Min Act: -0.0000

Data Index: 910492 (C4 (Web Text))

Max Activating Token Index: 281