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

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

Neuron 119 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: 0.7210. Min Range: -0.7210

Max Act: 0.7210. Min Act: -0.0000

Data Index: 1008642 (C4 (Web Text))

Max Activating Token Index: 1000

Text #1

Max Range: 0.7210. Min Range: -0.7210

Max Act: 0.6791. Min Act: -0.0000

Data Index: 418151 (C4 (Web Text))

Max Activating Token Index: 910

Text #2

Max Range: 0.7210. Min Range: -0.7210

Max Act: 0.6241. Min Act: 0.0001

Data Index: 695055 (C4 (Web Text))

Max Activating Token Index: 563

Text #3

Max Range: 0.7210. Min Range: -0.7210

Max Act: 0.6183. Min Act: -0.0000

Data Index: 1002105 (C4 (Web Text))

Max Activating Token Index: 681

Text #4

Max Range: 0.7210. Min Range: -0.7210

Max Act: 0.5828. Min Act: -0.0000

Data Index: 1121718 (C4 (Web Text))

Max Activating Token Index: 569

Text #5

Max Range: 0.7210. Min Range: -0.7210

Max Act: 0.5430. Min Act: 0.0001

Data Index: 851202 (C4 (Web Text))

Max Activating Token Index: 110

Text #6

Max Range: 0.7210. Min Range: -0.7210

Max Act: 0.5334. Min Act: -0.0000

Data Index: 730916 (C4 (Web Text))

Max Activating Token Index: 856

Text #7

Max Range: 0.7210. Min Range: -0.7210

Max Act: 0.5332. Min Act: 0.0001

Data Index: 239257 (C4 (Web Text))

Max Activating Token Index: 192

Text #8

Max Range: 0.7210. Min Range: -0.7210

Max Act: 0.5341. Min Act: 0.0000

Data Index: 1153140 (C4 (Web Text))

Max Activating Token Index: 582

Text #9

Max Range: 0.7210. Min Range: -0.7210

Max Act: 0.5479. Min Act: -0.0000

Data Index: 348201 (C4 (Web Text))

Max Activating Token Index: 848

Text #10

Max Range: 0.7210. Min Range: -0.7210

Max Act: 0.4550. Min Act: -0.0000

Data Index: 629347 (C4 (Web Text))

Max Activating Token Index: 715

Text #11

Max Range: 0.7210. Min Range: -0.7210

Max Act: 0.4686. Min Act: -0.0000

Data Index: 934503 (C4 (Web Text))

Max Activating Token Index: 707

Text #12

Max Range: 0.7210. Min Range: -0.7210

Max Act: 0.4564. Min Act: -0.0000

Data Index: 309860 (C4 (Web Text))

Max Activating Token Index: 680

Text #13

Max Range: 0.7210. Min Range: -0.7210

Max Act: 0.4634. Min Act: -0.0000

Data Index: 1263032 (C4 (Web Text))

Max Activating Token Index: 1001

Text #14

Max Range: 0.7210. Min Range: -0.7210

Max Act: 0.4619. Min Act: -0.0000

Data Index: 284255 (C4 (Web Text))

Max Activating Token Index: 569

Text #15

Max Range: 0.7210. Min Range: -0.7210

Max Act: 0.4545. Min Act: 0.0001

Data Index: 206803 (C4 (Web Text))

Max Activating Token Index: 450

Text #16

Max Range: 0.7210. Min Range: -0.7210

Max Act: 0.4565. Min Act: 0.0000

Data Index: 938383 (C4 (Web Text))

Max Activating Token Index: 425

Text #17

Max Range: 0.7210. Min Range: -0.7210

Max Act: 0.4670. Min Act: -0.0000

Data Index: 968846 (C4 (Web Text))

Max Activating Token Index: 872

Text #18

Max Range: 0.7210. Min Range: -0.7210

Max Act: 0.4669. Min Act: -0.0000

Data Index: 757270 (C4 (Web Text))

Max Activating Token Index: 367

Text #19

Max Range: 0.7210. Min Range: -0.7210

Max Act: 0.4513. Min Act: 0.0000

Data Index: 1265826 (C4 (Web Text))

Max Activating Token Index: 686