Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2706 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7970. Min Range: -0.7970

Max Act: 0.7962. Min Act: -0.0001

Data Index: 677247 (C4 (Web Text))

Max Activating Token Index: 538

Text #1

Max Range: 0.7970. Min Range: -0.7970

Max Act: 0.7970. Min Act: -0.0001

Data Index: 540552 (C4 (Web Text))

Max Activating Token Index: 273

Text #2

Max Range: 0.7970. Min Range: -0.7970

Max Act: 0.7934. Min Act: -0.0001

Data Index: 783743 (C4 (Web Text))

Max Activating Token Index: 559

Text #3

Max Range: 0.7970. Min Range: -0.7970

Max Act: 0.7886. Min Act: -0.0001

Data Index: 721969 (C4 (Web Text))

Max Activating Token Index: 941

Text #4

Max Range: 0.7970. Min Range: -0.7970

Max Act: 0.7850. Min Act: -0.0001

Data Index: 1050994 (C4 (Web Text))

Max Activating Token Index: 686

Text #5

Max Range: 0.7970. Min Range: -0.7970

Max Act: 0.7510. Min Act: -0.0001

Data Index: 976987 (C4 (Web Text))

Max Activating Token Index: 990

Text #6

Max Range: 0.7970. Min Range: -0.7970

Max Act: 0.7369. Min Act: -0.0001

Data Index: 590240 (C4 (Web Text))

Max Activating Token Index: 176

Text #7

Max Range: 0.7970. Min Range: -0.7970

Max Act: 0.7616. Min Act: -0.0001

Data Index: 1342499 (C4 (Web Text))

Max Activating Token Index: 71

Text #8

Max Range: 0.7970. Min Range: -0.7970

Max Act: 0.7599. Min Act: -0.0001

Data Index: 1241760 (C4 (Web Text))

Max Activating Token Index: 735

Text #9

Max Range: 0.7970. Min Range: -0.7970

Max Act: 0.7507. Min Act: -0.0001

Data Index: 265945 (C4 (Web Text))

Max Activating Token Index: 471

Text #10

Max Range: 0.7970. Min Range: -0.7970

Max Act: 0.7757. Min Act: -0.0001

Data Index: 507248 (C4 (Web Text))

Max Activating Token Index: 980

Text #11

Max Range: 0.7970. Min Range: -0.7970

Max Act: 0.7650. Min Act: -0.0001

Data Index: 459829 (C4 (Web Text))

Max Activating Token Index: 858

Text #12

Max Range: 0.7970. Min Range: -0.7970

Max Act: 0.7599. Min Act: -0.0001

Data Index: 59895 (C4 (Web Text))

Max Activating Token Index: 587

Text #13

Max Range: 0.7970. Min Range: -0.7970

Max Act: 0.6936. Min Act: -0.0001

Data Index: 1319462 (C4 (Web Text))

Max Activating Token Index: 951

Text #14

Max Range: 0.7970. Min Range: -0.7970

Max Act: 0.6890. Min Act: -0.0001

Data Index: 412348 (C4 (Web Text))

Max Activating Token Index: 926

Text #15

Max Range: 0.7970. Min Range: -0.7970

Max Act: 0.7290. Min Act: -0.0001

Data Index: 1200216 (C4 (Web Text))

Max Activating Token Index: 819

Text #16

Max Range: 0.7970. Min Range: -0.7970

Max Act: 0.7523. Min Act: -0.0001

Data Index: 472974 (C4 (Web Text))

Max Activating Token Index: 976

Text #17

Max Range: 0.7970. Min Range: -0.7970

Max Act: 0.7296. Min Act: -0.0001

Data Index: 750165 (C4 (Web Text))

Max Activating Token Index: 948

Text #18

Max Range: 0.7970. Min Range: -0.7970

Max Act: 0.7224. Min Act: -0.0001

Data Index: 1062676 (C4 (Web Text))

Max Activating Token Index: 901

Text #19

Max Range: 0.7970. Min Range: -0.7970

Max Act: 0.7073. Min Act: -0.0001

Data Index: 748311 (C4 (Web Text))

Max Activating Token Index: 512