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

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

Neuron 6081 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3020. Min Range: -0.3020

Max Act: 0.3020. Min Act: -0.0000

Data Index: 1087927 (C4 (Web Text))

Max Activating Token Index: 205

Text #1

Max Range: 0.3020. Min Range: -0.3020

Max Act: 0.2963. Min Act: -0.0000

Data Index: 496205 (C4 (Web Text))

Max Activating Token Index: 695

Text #2

Max Range: 0.3020. Min Range: -0.3020

Max Act: 0.2964. Min Act: -0.0000

Data Index: 69045 (C4 (Web Text))

Max Activating Token Index: 809

Text #3

Max Range: 0.3020. Min Range: -0.3020

Max Act: 0.2744. Min Act: -0.0000

Data Index: 947155 (C4 (Web Text))

Max Activating Token Index: 889

Text #4

Max Range: 0.3020. Min Range: -0.3020

Max Act: 0.2346. Min Act: -0.0000

Data Index: 585963 (C4 (Web Text))

Max Activating Token Index: 559

Text #5

Max Range: 0.3020. Min Range: -0.3020

Max Act: 0.2423. Min Act: -0.0000

Data Index: 1205377 (C4 (Web Text))

Max Activating Token Index: 862

Text #6

Max Range: 0.3020. Min Range: -0.3020

Max Act: 0.2333. Min Act: -0.0000

Data Index: 638477 (C4 (Web Text))

Max Activating Token Index: 796

Text #7

Max Range: 0.3020. Min Range: -0.3020

Max Act: 0.2280. Min Act: -0.0000

Data Index: 301877 (C4 (Web Text))

Max Activating Token Index: 758

Text #8

Max Range: 0.3020. Min Range: -0.3020

Max Act: 0.2547. Min Act: -0.0000

Data Index: 307313 (C4 (Web Text))

Max Activating Token Index: 664

Text #9

Max Range: 0.3020. Min Range: -0.3020

Max Act: 0.1952. Min Act: -0.0000

Data Index: 1171547 (C4 (Web Text))

Max Activating Token Index: 642

Text #10

Max Range: 0.3020. Min Range: -0.3020

Max Act: 0.1958. Min Act: -0.0000

Data Index: 295419 (C4 (Web Text))

Max Activating Token Index: 640

Text #11

Max Range: 0.3020. Min Range: -0.3020

Max Act: 0.2388. Min Act: -0.0000

Data Index: 808773 (C4 (Web Text))

Max Activating Token Index: 404

Text #12

Max Range: 0.3020. Min Range: -0.3020

Max Act: 0.2017. Min Act: -0.0000

Data Index: 1117406 (C4 (Web Text))

Max Activating Token Index: 120

Text #13

Max Range: 0.3020. Min Range: -0.3020

Max Act: 0.2130. Min Act: -0.0000

Data Index: 600736 (C4 (Web Text))

Max Activating Token Index: 132

Text #14

Max Range: 0.3020. Min Range: -0.3020

Max Act: 0.2178. Min Act: -0.0000

Data Index: 765126 (C4 (Web Text))

Max Activating Token Index: 841

Text #15

Max Range: 0.3020. Min Range: -0.3020

Max Act: 0.1901. Min Act: -0.0000

Data Index: 1285118 (C4 (Web Text))

Max Activating Token Index: 47

Text #16

Max Range: 0.3020. Min Range: -0.3020

Max Act: 0.1879. Min Act: -0.0000

Data Index: 273278 (C4 (Web Text))

Max Activating Token Index: 908

Text #17

Max Range: 0.3020. Min Range: -0.3020

Max Act: 0.1913. Min Act: -0.0000

Data Index: 1476338 (Python Code)

Max Activating Token Index: 100

Text #18

Max Range: 0.3020. Min Range: -0.3020

Max Act: 0.1944. Min Act: -0.0000

Data Index: 615163 (C4 (Web Text))

Max Activating Token Index: 422

Text #19

Max Range: 0.3020. Min Range: -0.3020

Max Act: 0.2078. Min Act: -0.0000

Data Index: 1039434 (C4 (Web Text))

Max Activating Token Index: 212