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

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

Neuron 2977 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7541. Min Range: -0.7541

Max Act: 0.7541. Min Act: -0.0000

Data Index: 780548 (C4 (Web Text))

Max Activating Token Index: 847

Text #1

Max Range: 0.7541. Min Range: -0.7541

Max Act: 0.6999. Min Act: -0.0000

Data Index: 34541 (C4 (Web Text))

Max Activating Token Index: 877

Text #2

Max Range: 0.7541. Min Range: -0.7541

Max Act: 0.6480. Min Act: 0.0000

Data Index: 1047379 (C4 (Web Text))

Max Activating Token Index: 849

Text #3

Max Range: 0.7541. Min Range: -0.7541

Max Act: 0.6884. Min Act: 0.0000

Data Index: 1313836 (C4 (Web Text))

Max Activating Token Index: 77

Text #4

Max Range: 0.7541. Min Range: -0.7541

Max Act: 0.6588. Min Act: -0.0000

Data Index: 371969 (C4 (Web Text))

Max Activating Token Index: 239

Text #5

Max Range: 0.7541. Min Range: -0.7541

Max Act: 0.6658. Min Act: -0.0000

Data Index: 234918 (C4 (Web Text))

Max Activating Token Index: 574

Text #6

Max Range: 0.7541. Min Range: -0.7541

Max Act: 0.6413. Min Act: 0.0000

Data Index: 588439 (C4 (Web Text))

Max Activating Token Index: 518

Text #7

Max Range: 0.7541. Min Range: -0.7541

Max Act: 0.6407. Min Act: -0.0000

Data Index: 91844 (C4 (Web Text))

Max Activating Token Index: 374

Text #8

Max Range: 0.7541. Min Range: -0.7541

Max Act: 0.6275. Min Act: -0.0000

Data Index: 832998 (C4 (Web Text))

Max Activating Token Index: 441

Text #9

Max Range: 0.7541. Min Range: -0.7541

Max Act: 0.5961. Min Act: -0.0000

Data Index: 95925 (C4 (Web Text))

Max Activating Token Index: 111

Text #10

Max Range: 0.7541. Min Range: -0.7541

Max Act: 0.6612. Min Act: -0.0000

Data Index: 1631034 (Python Code)

Max Activating Token Index: 322

Text #11

Max Range: 0.7541. Min Range: -0.7541

Max Act: 0.5903. Min Act: -0.0000

Data Index: 1223812 (C4 (Web Text))

Max Activating Token Index: 939

Text #12

Max Range: 0.7541. Min Range: -0.7541

Max Act: 0.6191. Min Act: -0.0000

Data Index: 334665 (C4 (Web Text))

Max Activating Token Index: 92

Text #13

Max Range: 0.7541. Min Range: -0.7541

Max Act: 0.6026. Min Act: -0.0000

Data Index: 825861 (C4 (Web Text))

Max Activating Token Index: 386

Text #14

Max Range: 0.7541. Min Range: -0.7541

Max Act: 0.5923. Min Act: -0.0000

Data Index: 421026 (C4 (Web Text))

Max Activating Token Index: 348

Text #15

Max Range: 0.7541. Min Range: -0.7541

Max Act: 0.5252. Min Act: -0.0000

Data Index: 1482697 (Python Code)

Max Activating Token Index: 740

Text #16

Max Range: 0.7541. Min Range: -0.7541

Max Act: 0.5882. Min Act: -0.0000

Data Index: 82078 (C4 (Web Text))

Max Activating Token Index: 808

Text #17

Max Range: 0.7541. Min Range: -0.7541

Max Act: 0.5879. Min Act: -0.0000

Data Index: 1024382 (C4 (Web Text))

Max Activating Token Index: 425

Text #18

Max Range: 0.7541. Min Range: -0.7541

Max Act: 0.6144. Min Act: -0.0000

Data Index: 593732 (C4 (Web Text))

Max Activating Token Index: 989

Text #19

Max Range: 0.7541. Min Range: -0.7541

Max Act: 0.5284. Min Act: -0.0000

Data Index: 495248 (C4 (Web Text))

Max Activating Token Index: 927