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

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

Neuron 4367 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7216. Min Range: -0.7216

Max Act: 0.7216. Min Act: -0.0000

Data Index: 160703 (C4 (Web Text))

Max Activating Token Index: 744

Text #1

Max Range: 0.7216. Min Range: -0.7216

Max Act: 0.6773. Min Act: -0.0000

Data Index: 783580 (C4 (Web Text))

Max Activating Token Index: 692

Text #2

Max Range: 0.7216. Min Range: -0.7216

Max Act: 0.6803. Min Act: -0.0000

Data Index: 993142 (C4 (Web Text))

Max Activating Token Index: 818

Text #3

Max Range: 0.7216. Min Range: -0.7216

Max Act: 0.5963. Min Act: -0.0001

Data Index: 327305 (C4 (Web Text))

Max Activating Token Index: 923

Text #4

Max Range: 0.7216. Min Range: -0.7216

Max Act: 0.6895. Min Act: -0.0000

Data Index: 101323 (C4 (Web Text))

Max Activating Token Index: 676

Text #5

Max Range: 0.7216. Min Range: -0.7216

Max Act: 0.5155. Min Act: -0.0000

Data Index: 276890 (C4 (Web Text))

Max Activating Token Index: 898

Text #6

Max Range: 0.7216. Min Range: -0.7216

Max Act: 0.6302. Min Act: -0.0000

Data Index: 146724 (C4 (Web Text))

Max Activating Token Index: 782

Text #7

Max Range: 0.7216. Min Range: -0.7216

Max Act: 0.6360. Min Act: -0.0000

Data Index: 701952 (C4 (Web Text))

Max Activating Token Index: 440

Text #8

Max Range: 0.7216. Min Range: -0.7216

Max Act: 0.6044. Min Act: -0.0000

Data Index: 1167163 (C4 (Web Text))

Max Activating Token Index: 372

Text #9

Max Range: 0.7216. Min Range: -0.7216

Max Act: 0.5965. Min Act: -0.0001

Data Index: 327934 (C4 (Web Text))

Max Activating Token Index: 618

Text #10

Max Range: 0.7216. Min Range: -0.7216

Max Act: 0.6514. Min Act: -0.0000

Data Index: 795735 (C4 (Web Text))

Max Activating Token Index: 342

Text #11

Max Range: 0.7216. Min Range: -0.7216

Max Act: 0.5703. Min Act: -0.0000

Data Index: 575247 (C4 (Web Text))

Max Activating Token Index: 785

Text #12

Max Range: 0.7216. Min Range: -0.7216

Max Act: 0.5690. Min Act: -0.0000

Data Index: 489725 (C4 (Web Text))

Max Activating Token Index: 123

Text #13

Max Range: 0.7216. Min Range: -0.7216

Max Act: 0.5052. Min Act: -0.0000

Data Index: 963095 (C4 (Web Text))

Max Activating Token Index: 744

Text #14

Max Range: 0.7216. Min Range: -0.7216

Max Act: 0.5515. Min Act: -0.0000

Data Index: 267755 (C4 (Web Text))

Max Activating Token Index: 497

Text #15

Max Range: 0.7216. Min Range: -0.7216

Max Act: 0.5747. Min Act: -0.0000

Data Index: 1070585 (C4 (Web Text))

Max Activating Token Index: 852

Text #16

Max Range: 0.7216. Min Range: -0.7216

Max Act: 0.5552. Min Act: -0.0000

Data Index: 118139 (C4 (Web Text))

Max Activating Token Index: 586

Text #17

Max Range: 0.7216. Min Range: -0.7216

Max Act: 0.5634. Min Act: -0.0001

Data Index: 1269796 (C4 (Web Text))

Max Activating Token Index: 584

Text #18

Max Range: 0.7216. Min Range: -0.7216

Max Act: 0.5568. Min Act: -0.0000

Data Index: 1066662 (C4 (Web Text))

Max Activating Token Index: 656

Text #19

Max Range: 0.7216. Min Range: -0.7216

Max Act: 0.6671. Min Act: -0.0000

Data Index: 1176165 (C4 (Web Text))

Max Activating Token Index: 402