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

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

Neuron 195 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1288. Min Range: -0.1288

Max Act: 0.1288. Min Act: -0.0001

Data Index: 1207510 (C4 (Web Text))

Max Activating Token Index: 568

Text #1

Max Range: 0.1288. Min Range: -0.1288

Max Act: 0.1208. Min Act: -0.0001

Data Index: 92981 (C4 (Web Text))

Max Activating Token Index: 649

Text #2

Max Range: 0.1288. Min Range: -0.1288

Max Act: 0.1136. Min Act: -0.0001

Data Index: 73481 (C4 (Web Text))

Max Activating Token Index: 921

Text #3

Max Range: 0.1288. Min Range: -0.1288

Max Act: 0.0974. Min Act: -0.0001

Data Index: 1334508 (C4 (Web Text))

Max Activating Token Index: 450

Text #4

Max Range: 0.1288. Min Range: -0.1288

Max Act: 0.1043. Min Act: -0.0001

Data Index: 1049452 (C4 (Web Text))

Max Activating Token Index: 72

Text #5

Max Range: 0.1288. Min Range: -0.1288

Max Act: 0.1005. Min Act: -0.0002

Data Index: 228313 (C4 (Web Text))

Max Activating Token Index: 854

Text #6

Max Range: 0.1288. Min Range: -0.1288

Max Act: 0.0980. Min Act: -0.0001

Data Index: 73562 (C4 (Web Text))

Max Activating Token Index: 849

Text #7

Max Range: 0.1288. Min Range: -0.1288

Max Act: 0.0925. Min Act: -0.0001

Data Index: 756426 (C4 (Web Text))

Max Activating Token Index: 423

Text #8

Max Range: 0.1288. Min Range: -0.1288

Max Act: 0.0856. Min Act: -0.0001

Data Index: 40584 (C4 (Web Text))

Max Activating Token Index: 879

Text #9

Max Range: 0.1288. Min Range: -0.1288

Max Act: 0.0935. Min Act: -0.0001

Data Index: 70572 (C4 (Web Text))

Max Activating Token Index: 684

Text #10

Max Range: 0.1288. Min Range: -0.1288

Max Act: 0.0955. Min Act: -0.0001

Data Index: 635661 (C4 (Web Text))

Max Activating Token Index: 255

Text #11

Max Range: 0.1288. Min Range: -0.1288

Max Act: 0.0935. Min Act: -0.0001

Data Index: 1222340 (C4 (Web Text))

Max Activating Token Index: 904

Text #12

Max Range: 0.1288. Min Range: -0.1288

Max Act: 0.0869. Min Act: -0.0001

Data Index: 863347 (C4 (Web Text))

Max Activating Token Index: 167

Text #13

Max Range: 0.1288. Min Range: -0.1288

Max Act: 0.0831. Min Act: -0.0001

Data Index: 309115 (C4 (Web Text))

Max Activating Token Index: 934

Text #14

Max Range: 0.1288. Min Range: -0.1288

Max Act: 0.0887. Min Act: -0.0001

Data Index: 575999 (C4 (Web Text))

Max Activating Token Index: 701

Text #15

Max Range: 0.1288. Min Range: -0.1288

Max Act: 0.0878. Min Act: -0.0001

Data Index: 779196 (C4 (Web Text))

Max Activating Token Index: 358

Text #16

Max Range: 0.1288. Min Range: -0.1288

Max Act: 0.0865. Min Act: -0.0001

Data Index: 761389 (C4 (Web Text))

Max Activating Token Index: 611

Text #17

Max Range: 0.1288. Min Range: -0.1288

Max Act: 0.0868. Min Act: -0.0001

Data Index: 1137070 (C4 (Web Text))

Max Activating Token Index: 951

Text #18

Max Range: 0.1288. Min Range: -0.1288

Max Act: 0.0899. Min Act: -0.0001

Data Index: 1250002 (C4 (Web Text))

Max Activating Token Index: 451

Text #19

Max Range: 0.1288. Min Range: -0.1288

Max Act: 0.0829. Min Act: -0.0001

Data Index: 675417 (C4 (Web Text))

Max Activating Token Index: 616