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

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

Neuron 1309 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9290. Min Range: -0.9290

Max Act: 0.9290. Min Act: -0.0000

Data Index: 92927 (C4 (Web Text))

Max Activating Token Index: 627

Text #1

Max Range: 0.9290. Min Range: -0.9290

Max Act: 0.8279. Min Act: -0.0000

Data Index: 1132183 (C4 (Web Text))

Max Activating Token Index: 729

Text #2

Max Range: 0.9290. Min Range: -0.9290

Max Act: 0.7708. Min Act: -0.0000

Data Index: 353882 (C4 (Web Text))

Max Activating Token Index: 181

Text #3

Max Range: 0.9290. Min Range: -0.9290

Max Act: 0.6096. Min Act: -0.0000

Data Index: 759106 (C4 (Web Text))

Max Activating Token Index: 793

Text #4

Max Range: 0.9290. Min Range: -0.9290

Max Act: 0.5554. Min Act: -0.0000

Data Index: 67570 (C4 (Web Text))

Max Activating Token Index: 53

Text #5

Max Range: 0.9290. Min Range: -0.9290

Max Act: 0.5697. Min Act: -0.0000

Data Index: 85586 (C4 (Web Text))

Max Activating Token Index: 305

Text #6

Max Range: 0.9290. Min Range: -0.9290

Max Act: 0.4958. Min Act: -0.0000

Data Index: 50572 (C4 (Web Text))

Max Activating Token Index: 294

Text #7

Max Range: 0.9290. Min Range: -0.9290

Max Act: 0.5128. Min Act: 0.0000

Data Index: 476487 (C4 (Web Text))

Max Activating Token Index: 54

Text #8

Max Range: 0.9290. Min Range: -0.9290

Max Act: 0.4560. Min Act: -0.0000

Data Index: 1191 (C4 (Web Text))

Max Activating Token Index: 923

Text #9

Max Range: 0.9290. Min Range: -0.9290

Max Act: 0.4620. Min Act: -0.0000

Data Index: 750063 (C4 (Web Text))

Max Activating Token Index: 992

Text #10

Max Range: 0.9290. Min Range: -0.9290

Max Act: 0.4720. Min Act: -0.0000

Data Index: 725026 (C4 (Web Text))

Max Activating Token Index: 971

Text #11

Max Range: 0.9290. Min Range: -0.9290

Max Act: 0.4918. Min Act: -0.0000

Data Index: 557485 (C4 (Web Text))

Max Activating Token Index: 243

Text #12

Max Range: 0.9290. Min Range: -0.9290

Max Act: 0.4509. Min Act: -0.0000

Data Index: 397992 (C4 (Web Text))

Max Activating Token Index: 382

Text #13

Max Range: 0.9290. Min Range: -0.9290

Max Act: 0.4430. Min Act: -0.0000

Data Index: 424282 (C4 (Web Text))

Max Activating Token Index: 68

Text #14

Max Range: 0.9290. Min Range: -0.9290

Max Act: 0.4271. Min Act: -0.0000

Data Index: 609320 (C4 (Web Text))

Max Activating Token Index: 591

Text #15

Max Range: 0.9290. Min Range: -0.9290

Max Act: 0.4308. Min Act: -0.0000

Data Index: 708097 (C4 (Web Text))

Max Activating Token Index: 402

Text #16

Max Range: 0.9290. Min Range: -0.9290

Max Act: 0.4175. Min Act: -0.0000

Data Index: 1115401 (C4 (Web Text))

Max Activating Token Index: 606

Text #17

Max Range: 0.9290. Min Range: -0.9290

Max Act: 0.4074. Min Act: -0.0000

Data Index: 1085464 (C4 (Web Text))

Max Activating Token Index: 604

Text #18

Max Range: 0.9290. Min Range: -0.9290

Max Act: 0.3508. Min Act: -0.0000

Data Index: 845264 (C4 (Web Text))

Max Activating Token Index: 385

Text #19

Max Range: 0.9290. Min Range: -0.9290

Max Act: 0.4429. Min Act: -0.0000

Data Index: 1213366 (C4 (Web Text))

Max Activating Token Index: 61