Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2307 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.4934. Min Range: -1.4934

Max Act: 1.4934. Min Act: -0.0000

Data Index: 605869 (C4 (Web Text))

Max Activating Token Index: 930

Text #1

Max Range: 1.4934. Min Range: -1.4934

Max Act: 1.1047. Min Act: -0.0000

Data Index: 220858 (C4 (Web Text))

Max Activating Token Index: 483

Text #2

Max Range: 1.4934. Min Range: -1.4934

Max Act: 1.0970. Min Act: -0.0000

Data Index: 1077437 (C4 (Web Text))

Max Activating Token Index: 174

Text #3

Max Range: 1.4934. Min Range: -1.4934

Max Act: 0.9936. Min Act: -0.0000

Data Index: 122790 (C4 (Web Text))

Max Activating Token Index: 463

Text #4

Max Range: 1.4934. Min Range: -1.4934

Max Act: 1.0039. Min Act: -0.0000

Data Index: 1051501 (C4 (Web Text))

Max Activating Token Index: 13

Text #5

Max Range: 1.4934. Min Range: -1.4934

Max Act: 1.0099. Min Act: -0.0000

Data Index: 1228667 (C4 (Web Text))

Max Activating Token Index: 72

Text #6

Max Range: 1.4934. Min Range: -1.4934

Max Act: 1.0167. Min Act: -0.0000

Data Index: 896811 (C4 (Web Text))

Max Activating Token Index: 503

Text #7

Max Range: 1.4934. Min Range: -1.4934

Max Act: 0.9513. Min Act: -0.0000

Data Index: 267996 (C4 (Web Text))

Max Activating Token Index: 110

Text #8

Max Range: 1.4934. Min Range: -1.4934

Max Act: 0.8838. Min Act: -0.0000

Data Index: 236431 (C4 (Web Text))

Max Activating Token Index: 493

Text #9

Max Range: 1.4934. Min Range: -1.4934

Max Act: 0.9513. Min Act: -0.0000

Data Index: 134586 (C4 (Web Text))

Max Activating Token Index: 209

Text #10

Max Range: 1.4934. Min Range: -1.4934

Max Act: 0.9163. Min Act: -0.0000

Data Index: 1258606 (C4 (Web Text))

Max Activating Token Index: 55

Text #11

Max Range: 1.4934. Min Range: -1.4934

Max Act: 0.9126. Min Act: -0.0000

Data Index: 489773 (C4 (Web Text))

Max Activating Token Index: 57

Text #12

Max Range: 1.4934. Min Range: -1.4934

Max Act: 0.8688. Min Act: -0.0000

Data Index: 400295 (C4 (Web Text))

Max Activating Token Index: 301

Text #13

Max Range: 1.4934. Min Range: -1.4934

Max Act: 0.8827. Min Act: -0.0000

Data Index: 252336 (C4 (Web Text))

Max Activating Token Index: 536

Text #14

Max Range: 1.4934. Min Range: -1.4934

Max Act: 0.9163. Min Act: -0.0000

Data Index: 806160 (C4 (Web Text))

Max Activating Token Index: 735

Text #15

Max Range: 1.4934. Min Range: -1.4934

Max Act: 0.8679. Min Act: -0.0000

Data Index: 882918 (C4 (Web Text))

Max Activating Token Index: 394

Text #16

Max Range: 1.4934. Min Range: -1.4934

Max Act: 0.8322. Min Act: -0.0000

Data Index: 772609 (C4 (Web Text))

Max Activating Token Index: 545

Text #17

Max Range: 1.4934. Min Range: -1.4934

Max Act: 0.8695. Min Act: -0.0000

Data Index: 319958 (C4 (Web Text))

Max Activating Token Index: 227

Text #18

Max Range: 1.4934. Min Range: -1.4934

Max Act: 0.8633. Min Act: -0.0000

Data Index: 1184917 (C4 (Web Text))

Max Activating Token Index: 748

Text #19

Max Range: 1.4934. Min Range: -1.4934

Max Act: 0.9212. Min Act: -0.0000

Data Index: 251458 (C4 (Web Text))

Max Activating Token Index: 296