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

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

Neuron 4547 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: 0.1169. Min Range: -0.1169

Max Act: 0.1169. Min Act: -0.0001

Data Index: 255861 (C4 (Web Text))

Max Activating Token Index: 227

Text #1

Max Range: 0.1169. Min Range: -0.1169

Max Act: 0.1099. Min Act: -0.0000

Data Index: 371582 (C4 (Web Text))

Max Activating Token Index: 778

Text #2

Max Range: 0.1169. Min Range: -0.1169

Max Act: 0.1086. Min Act: -0.0000

Data Index: 1024791 (C4 (Web Text))

Max Activating Token Index: 437

Text #3

Max Range: 0.1169. Min Range: -0.1169

Max Act: 0.1082. Min Act: -0.0000

Data Index: 40138 (C4 (Web Text))

Max Activating Token Index: 575

Text #4

Max Range: 0.1169. Min Range: -0.1169

Max Act: 0.1028. Min Act: -0.0001

Data Index: 199614 (C4 (Web Text))

Max Activating Token Index: 318

Text #5

Max Range: 0.1169. Min Range: -0.1169

Max Act: 0.1008. Min Act: -0.0000

Data Index: 267278 (C4 (Web Text))

Max Activating Token Index: 320

Text #6

Max Range: 0.1169. Min Range: -0.1169

Max Act: 0.1033. Min Act: -0.0000

Data Index: 95735 (C4 (Web Text))

Max Activating Token Index: 624

Text #7

Max Range: 0.1169. Min Range: -0.1169

Max Act: 0.1028. Min Act: -0.0000

Data Index: 306670 (C4 (Web Text))

Max Activating Token Index: 523

Text #8

Max Range: 0.1169. Min Range: -0.1169

Max Act: 0.0977. Min Act: -0.0000

Data Index: 536699 (C4 (Web Text))

Max Activating Token Index: 956

Text #9

Max Range: 0.1169. Min Range: -0.1169

Max Act: 0.0926. Min Act: -0.0001

Data Index: 679717 (C4 (Web Text))

Max Activating Token Index: 55

Text #10

Max Range: 0.1169. Min Range: -0.1169

Max Act: 0.0913. Min Act: -0.0000

Data Index: 1231957 (C4 (Web Text))

Max Activating Token Index: 969

Text #11

Max Range: 0.1169. Min Range: -0.1169

Max Act: 0.0921. Min Act: -0.0000

Data Index: 581020 (C4 (Web Text))

Max Activating Token Index: 411

Text #12

Max Range: 0.1169. Min Range: -0.1169

Max Act: 0.0936. Min Act: -0.0001

Data Index: 942817 (C4 (Web Text))

Max Activating Token Index: 976

Text #13

Max Range: 0.1169. Min Range: -0.1169

Max Act: 0.0930. Min Act: -0.0000

Data Index: 138590 (C4 (Web Text))

Max Activating Token Index: 306

Text #14

Max Range: 0.1169. Min Range: -0.1169

Max Act: 0.0899. Min Act: -0.0000

Data Index: 883510 (C4 (Web Text))

Max Activating Token Index: 378

Text #15

Max Range: 0.1169. Min Range: -0.1169

Max Act: 0.0883. Min Act: -0.0000

Data Index: 198904 (C4 (Web Text))

Max Activating Token Index: 498

Text #16

Max Range: 0.1169. Min Range: -0.1169

Max Act: 0.0854. Min Act: -0.0000

Data Index: 635120 (C4 (Web Text))

Max Activating Token Index: 725

Text #17

Max Range: 0.1169. Min Range: -0.1169

Max Act: 0.0877. Min Act: -0.0000

Data Index: 27864 (C4 (Web Text))

Max Activating Token Index: 181

Text #18

Max Range: 0.1169. Min Range: -0.1169

Max Act: 0.0768. Min Act: -0.0000

Data Index: 279182 (C4 (Web Text))

Max Activating Token Index: 635

Text #19

Max Range: 0.1169. Min Range: -0.1169

Max Act: 0.0804. Min Act: -0.0000

Data Index: 490054 (C4 (Web Text))

Max Activating Token Index: 279