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

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

Neuron 1764 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: 0.5337. Min Range: -0.5337

Max Act: 0.5155. Min Act: -0.0001

Data Index: 430329 (C4 (Web Text))

Max Activating Token Index: 594

Text #1

Max Range: 0.5337. Min Range: -0.5337

Max Act: 0.4887. Min Act: -0.0001

Data Index: 63475 (C4 (Web Text))

Max Activating Token Index: 25

Text #2

Max Range: 0.5337. Min Range: -0.5337

Max Act: 0.5041. Min Act: -0.0001

Data Index: 686550 (C4 (Web Text))

Max Activating Token Index: 185

Text #3

Max Range: 0.5337. Min Range: -0.5337

Max Act: 0.3567. Min Act: -0.0001

Data Index: 742254 (C4 (Web Text))

Max Activating Token Index: 298

Text #4

Max Range: 0.5337. Min Range: -0.5337

Max Act: 0.4391. Min Act: -0.0001

Data Index: 437172 (C4 (Web Text))

Max Activating Token Index: 493

Text #5

Max Range: 0.5337. Min Range: -0.5337

Max Act: 0.4371. Min Act: -0.0001

Data Index: 557874 (C4 (Web Text))

Max Activating Token Index: 447

Text #6

Max Range: 0.5337. Min Range: -0.5337

Max Act: 0.3676. Min Act: -0.0001

Data Index: 245999 (C4 (Web Text))

Max Activating Token Index: 266

Text #7

Max Range: 0.5337. Min Range: -0.5337

Max Act: 0.4038. Min Act: -0.0001

Data Index: 930575 (C4 (Web Text))

Max Activating Token Index: 180

Text #8

Max Range: 0.5337. Min Range: -0.5337

Max Act: 0.4824. Min Act: -0.0001

Data Index: 1313394 (C4 (Web Text))

Max Activating Token Index: 674

Text #9

Max Range: 0.5337. Min Range: -0.5337

Max Act: 0.4509. Min Act: -0.0001

Data Index: 1162661 (C4 (Web Text))

Max Activating Token Index: 84

Text #10

Max Range: 0.5337. Min Range: -0.5337

Max Act: 0.4207. Min Act: -0.0001

Data Index: 599776 (C4 (Web Text))

Max Activating Token Index: 605

Text #11

Max Range: 0.5337. Min Range: -0.5337

Max Act: 0.4396. Min Act: -0.0001

Data Index: 352894 (C4 (Web Text))

Max Activating Token Index: 553

Text #12

Max Range: 0.5337. Min Range: -0.5337

Max Act: 0.4099. Min Act: -0.0001

Data Index: 1225275 (C4 (Web Text))

Max Activating Token Index: 738

Text #13

Max Range: 0.5337. Min Range: -0.5337

Max Act: 0.3671. Min Act: -0.0001

Data Index: 1062206 (C4 (Web Text))

Max Activating Token Index: 870

Text #14

Max Range: 0.5337. Min Range: -0.5337

Max Act: 0.4042. Min Act: -0.0001

Data Index: 4879 (C4 (Web Text))

Max Activating Token Index: 190

Text #15

Max Range: 0.5337. Min Range: -0.5337

Max Act: 0.3873. Min Act: -0.0001

Data Index: 1351307 (C4 (Web Text))

Max Activating Token Index: 896

Text #16

Max Range: 0.5337. Min Range: -0.5337

Max Act: 0.3765. Min Act: -0.0001

Data Index: 695575 (C4 (Web Text))

Max Activating Token Index: 633

Text #17

Max Range: 0.5337. Min Range: -0.5337

Max Act: 0.4287. Min Act: -0.0001

Data Index: 260343 (C4 (Web Text))

Max Activating Token Index: 107

Text #18

Max Range: 0.5337. Min Range: -0.5337

Max Act: 0.4045. Min Act: -0.0001

Data Index: 1322918 (C4 (Web Text))

Max Activating Token Index: 464

Text #19

Max Range: 0.5337. Min Range: -0.5337

Max Act: 0.5337. Min Act: -0.0001

Data Index: 96626 (C4 (Web Text))

Max Activating Token Index: 830