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

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

Neuron 1285 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5446. Min Range: -2.5446

Max Act: 2.5446. Min Act: -0.0000

Data Index: 935840 (C4 (Web Text))

Max Activating Token Index: 421

Text #1

Max Range: 2.5446. Min Range: -2.5446

Max Act: 2.3219. Min Act: 0.0000

Data Index: 207169 (C4 (Web Text))

Max Activating Token Index: 381

Text #2

Max Range: 2.5446. Min Range: -2.5446

Max Act: 2.0989. Min Act: -0.0000

Data Index: 655285 (C4 (Web Text))

Max Activating Token Index: 21

Text #3

Max Range: 2.5446. Min Range: -2.5446

Max Act: 2.0881. Min Act: -0.0000

Data Index: 570556 (C4 (Web Text))

Max Activating Token Index: 409

Text #4

Max Range: 2.5446. Min Range: -2.5446

Max Act: 1.9080. Min Act: -0.0000

Data Index: 146013 (C4 (Web Text))

Max Activating Token Index: 440

Text #5

Max Range: 2.5446. Min Range: -2.5446

Max Act: 1.8789. Min Act: -0.0000

Data Index: 179316 (C4 (Web Text))

Max Activating Token Index: 594

Text #6

Max Range: 2.5446. Min Range: -2.5446

Max Act: 1.8415. Min Act: -0.0000

Data Index: 137999 (C4 (Web Text))

Max Activating Token Index: 383

Text #7

Max Range: 2.5446. Min Range: -2.5446

Max Act: 1.7898. Min Act: -0.0000

Data Index: 946037 (C4 (Web Text))

Max Activating Token Index: 32

Text #8

Max Range: 2.5446. Min Range: -2.5446

Max Act: 1.7842. Min Act: -0.0000

Data Index: 359878 (C4 (Web Text))

Max Activating Token Index: 257

Text #9

Max Range: 2.5446. Min Range: -2.5446

Max Act: 1.7378. Min Act: -0.0000

Data Index: 958061 (C4 (Web Text))

Max Activating Token Index: 38

Text #10

Max Range: 2.5446. Min Range: -2.5446

Max Act: 1.6225. Min Act: 0.0000

Data Index: 141393 (C4 (Web Text))

Max Activating Token Index: 605

Text #11

Max Range: 2.5446. Min Range: -2.5446

Max Act: 1.7067. Min Act: -0.0000

Data Index: 720303 (C4 (Web Text))

Max Activating Token Index: 841

Text #12

Max Range: 2.5446. Min Range: -2.5446

Max Act: 1.6952. Min Act: -0.0000

Data Index: 269861 (C4 (Web Text))

Max Activating Token Index: 642

Text #13

Max Range: 2.5446. Min Range: -2.5446

Max Act: 1.6797. Min Act: -0.0000

Data Index: 1259507 (C4 (Web Text))

Max Activating Token Index: 524

Text #14

Max Range: 2.5446. Min Range: -2.5446

Max Act: 1.5834. Min Act: -0.0000

Data Index: 983784 (C4 (Web Text))

Max Activating Token Index: 714

Text #15

Max Range: 2.5446. Min Range: -2.5446

Max Act: 1.6419. Min Act: -0.0000

Data Index: 274902 (C4 (Web Text))

Max Activating Token Index: 822

Text #16

Max Range: 2.5446. Min Range: -2.5446

Max Act: 1.8438. Min Act: 0.0000

Data Index: 900773 (C4 (Web Text))

Max Activating Token Index: 308

Text #17

Max Range: 2.5446. Min Range: -2.5446

Max Act: 1.6355. Min Act: -0.0000

Data Index: 844718 (C4 (Web Text))

Max Activating Token Index: 764

Text #18

Max Range: 2.5446. Min Range: -2.5446

Max Act: 1.6342. Min Act: -0.0000

Data Index: 1292600 (C4 (Web Text))

Max Activating Token Index: 488

Text #19

Max Range: 2.5446. Min Range: -2.5446

Max Act: 1.6196. Min Act: -0.0000

Data Index: 483997 (C4 (Web Text))

Max Activating Token Index: 38