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

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

Neuron 4456 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8164. Min Range: -0.8164

Max Act: 0.8164. Min Act: -0.0000

Data Index: 1185511 (C4 (Web Text))

Max Activating Token Index: 880

Text #1

Max Range: 0.8164. Min Range: -0.8164

Max Act: 0.6544. Min Act: -0.0000

Data Index: 1114999 (C4 (Web Text))

Max Activating Token Index: 933

Text #2

Max Range: 0.8164. Min Range: -0.8164

Max Act: 0.6818. Min Act: -0.0000

Data Index: 313281 (C4 (Web Text))

Max Activating Token Index: 97

Text #3

Max Range: 0.8164. Min Range: -0.8164

Max Act: 0.6328. Min Act: -0.0000

Data Index: 142450 (C4 (Web Text))

Max Activating Token Index: 746

Text #4

Max Range: 0.8164. Min Range: -0.8164

Max Act: 0.6072. Min Act: -0.0000

Data Index: 226033 (C4 (Web Text))

Max Activating Token Index: 567

Text #5

Max Range: 0.8164. Min Range: -0.8164

Max Act: 0.6274. Min Act: -0.0000

Data Index: 346402 (C4 (Web Text))

Max Activating Token Index: 201

Text #6

Max Range: 0.8164. Min Range: -0.8164

Max Act: 0.5440. Min Act: -0.0000

Data Index: 452361 (C4 (Web Text))

Max Activating Token Index: 35

Text #7

Max Range: 0.8164. Min Range: -0.8164

Max Act: 0.6019. Min Act: -0.0000

Data Index: 639800 (C4 (Web Text))

Max Activating Token Index: 750

Text #8

Max Range: 0.8164. Min Range: -0.8164

Max Act: 0.5435. Min Act: -0.0000

Data Index: 1303352 (C4 (Web Text))

Max Activating Token Index: 1022

Text #9

Max Range: 0.8164. Min Range: -0.8164

Max Act: 0.5723. Min Act: -0.0000

Data Index: 583053 (C4 (Web Text))

Max Activating Token Index: 596

Text #10

Max Range: 0.8164. Min Range: -0.8164

Max Act: 0.5459. Min Act: -0.0000

Data Index: 466371 (C4 (Web Text))

Max Activating Token Index: 424

Text #11

Max Range: 0.8164. Min Range: -0.8164

Max Act: 0.5482. Min Act: -0.0000

Data Index: 791316 (C4 (Web Text))

Max Activating Token Index: 86

Text #12

Max Range: 0.8164. Min Range: -0.8164

Max Act: 0.5451. Min Act: -0.0000

Data Index: 608405 (C4 (Web Text))

Max Activating Token Index: 563

Text #13

Max Range: 0.8164. Min Range: -0.8164

Max Act: 0.5601. Min Act: -0.0000

Data Index: 718834 (C4 (Web Text))

Max Activating Token Index: 783

Text #14

Max Range: 0.8164. Min Range: -0.8164

Max Act: 0.5229. Min Act: -0.0000

Data Index: 1426 (C4 (Web Text))

Max Activating Token Index: 386

Text #15

Max Range: 0.8164. Min Range: -0.8164

Max Act: 0.5409. Min Act: -0.0000

Data Index: 506356 (C4 (Web Text))

Max Activating Token Index: 561

Text #16

Max Range: 0.8164. Min Range: -0.8164

Max Act: 0.5207. Min Act: -0.0000

Data Index: 1188873 (C4 (Web Text))

Max Activating Token Index: 551

Text #17

Max Range: 0.8164. Min Range: -0.8164

Max Act: 0.5531. Min Act: -0.0000

Data Index: 577701 (C4 (Web Text))

Max Activating Token Index: 981

Text #18

Max Range: 0.8164. Min Range: -0.8164

Max Act: 0.5460. Min Act: -0.0000

Data Index: 813348 (C4 (Web Text))

Max Activating Token Index: 283

Text #19

Max Range: 0.8164. Min Range: -0.8164

Max Act: 0.5092. Min Act: -0.0000

Data Index: 181647 (C4 (Web Text))

Max Activating Token Index: 549