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

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

Neuron 3114 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9433. Min Range: -0.9433

Max Act: 0.9433. Min Act: -0.0000

Data Index: 96868 (C4 (Web Text))

Max Activating Token Index: 948

Text #1

Max Range: 0.9433. Min Range: -0.9433

Max Act: 0.8551. Min Act: -0.0000

Data Index: 588098 (C4 (Web Text))

Max Activating Token Index: 184

Text #2

Max Range: 0.9433. Min Range: -0.9433

Max Act: 0.8253. Min Act: -0.0000

Data Index: 1109293 (C4 (Web Text))

Max Activating Token Index: 747

Text #3

Max Range: 0.9433. Min Range: -0.9433

Max Act: 0.8020. Min Act: -0.0000

Data Index: 39470 (C4 (Web Text))

Max Activating Token Index: 676

Text #4

Max Range: 0.9433. Min Range: -0.9433

Max Act: 0.8396. Min Act: -0.0000

Data Index: 1056225 (C4 (Web Text))

Max Activating Token Index: 825

Text #5

Max Range: 0.9433. Min Range: -0.9433

Max Act: 0.7386. Min Act: -0.0000

Data Index: 1107367 (C4 (Web Text))

Max Activating Token Index: 566

Text #6

Max Range: 0.9433. Min Range: -0.9433

Max Act: 0.7581. Min Act: -0.0000

Data Index: 1249118 (C4 (Web Text))

Max Activating Token Index: 362

Text #7

Max Range: 0.9433. Min Range: -0.9433

Max Act: 0.7736. Min Act: -0.0000

Data Index: 806068 (C4 (Web Text))

Max Activating Token Index: 110

Text #8

Max Range: 0.9433. Min Range: -0.9433

Max Act: 0.7150. Min Act: -0.0000

Data Index: 914217 (C4 (Web Text))

Max Activating Token Index: 911

Text #9

Max Range: 0.9433. Min Range: -0.9433

Max Act: 0.7084. Min Act: -0.0000

Data Index: 734431 (C4 (Web Text))

Max Activating Token Index: 728

Text #10

Max Range: 0.9433. Min Range: -0.9433

Max Act: 0.6942. Min Act: -0.0000

Data Index: 258497 (C4 (Web Text))

Max Activating Token Index: 638

Text #11

Max Range: 0.9433. Min Range: -0.9433

Max Act: 0.6467. Min Act: -0.0000

Data Index: 844512 (C4 (Web Text))

Max Activating Token Index: 696

Text #12

Max Range: 0.9433. Min Range: -0.9433

Max Act: 0.6843. Min Act: -0.0000

Data Index: 46647 (C4 (Web Text))

Max Activating Token Index: 281

Text #13

Max Range: 0.9433. Min Range: -0.9433

Max Act: 0.6837. Min Act: -0.0000

Data Index: 71442 (C4 (Web Text))

Max Activating Token Index: 461

Text #14

Max Range: 0.9433. Min Range: -0.9433

Max Act: 0.6596. Min Act: -0.0000

Data Index: 16248 (C4 (Web Text))

Max Activating Token Index: 604

Text #15

Max Range: 0.9433. Min Range: -0.9433

Max Act: 0.6301. Min Act: 0.0000

Data Index: 751039 (C4 (Web Text))

Max Activating Token Index: 925

Text #16

Max Range: 0.9433. Min Range: -0.9433

Max Act: 0.6384. Min Act: -0.0000

Data Index: 526897 (C4 (Web Text))

Max Activating Token Index: 212

Text #17

Max Range: 0.9433. Min Range: -0.9433

Max Act: 0.6381. Min Act: -0.0000

Data Index: 36904 (C4 (Web Text))

Max Activating Token Index: 443

Text #18

Max Range: 0.9433. Min Range: -0.9433

Max Act: 0.6130. Min Act: -0.0000

Data Index: 908602 (C4 (Web Text))

Max Activating Token Index: 499

Text #19

Max Range: 0.9433. Min Range: -0.9433

Max Act: 0.6460. Min Act: -0.0000

Data Index: 1294553 (C4 (Web Text))

Max Activating Token Index: 340