Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2390 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.0726. Min Range: -1.0726

Max Act: 1.0067. Min Act: -0.0000

Data Index: 369416 (C4 (Web Text))

Max Activating Token Index: 488

Text #1

Max Range: 1.0726. Min Range: -1.0726

Max Act: 1.0726. Min Act: -0.0000

Data Index: 1419210 (Python Code)

Max Activating Token Index: 256

Text #2

Max Range: 1.0726. Min Range: -1.0726

Max Act: 1.0685. Min Act: -0.0000

Data Index: 1200218 (C4 (Web Text))

Max Activating Token Index: 478

Text #3

Max Range: 1.0726. Min Range: -1.0726

Max Act: 0.9613. Min Act: -0.0000

Data Index: 318560 (C4 (Web Text))

Max Activating Token Index: 236

Text #4

Max Range: 1.0726. Min Range: -1.0726

Max Act: 0.9875. Min Act: -0.0000

Data Index: 1141095 (C4 (Web Text))

Max Activating Token Index: 340

Text #5

Max Range: 1.0726. Min Range: -1.0726

Max Act: 0.9392. Min Act: -0.0000

Data Index: 637113 (C4 (Web Text))

Max Activating Token Index: 209

Text #6

Max Range: 1.0726. Min Range: -1.0726

Max Act: 0.9081. Min Act: -0.0000

Data Index: 781369 (C4 (Web Text))

Max Activating Token Index: 197

Text #7

Max Range: 1.0726. Min Range: -1.0726

Max Act: 0.8788. Min Act: -0.0000

Data Index: 1147034 (C4 (Web Text))

Max Activating Token Index: 128

Text #8

Max Range: 1.0726. Min Range: -1.0726

Max Act: 0.9647. Min Act: -0.0000

Data Index: 350382 (C4 (Web Text))

Max Activating Token Index: 917

Text #9

Max Range: 1.0726. Min Range: -1.0726

Max Act: 0.9191. Min Act: -0.0000

Data Index: 617306 (C4 (Web Text))

Max Activating Token Index: 38

Text #10

Max Range: 1.0726. Min Range: -1.0726

Max Act: 0.8249. Min Act: -0.0000

Data Index: 1185937 (C4 (Web Text))

Max Activating Token Index: 416

Text #11

Max Range: 1.0726. Min Range: -1.0726

Max Act: 0.9500. Min Act: -0.0000

Data Index: 1414561 (Python Code)

Max Activating Token Index: 676

Text #12

Max Range: 1.0726. Min Range: -1.0726

Max Act: 0.8696. Min Act: -0.0000

Data Index: 873358 (C4 (Web Text))

Max Activating Token Index: 648

Text #13

Max Range: 1.0726. Min Range: -1.0726

Max Act: 0.8667. Min Act: -0.0000

Data Index: 364458 (C4 (Web Text))

Max Activating Token Index: 881

Text #14

Max Range: 1.0726. Min Range: -1.0726

Max Act: 0.8933. Min Act: -0.0000

Data Index: 540698 (C4 (Web Text))

Max Activating Token Index: 486

Text #15

Max Range: 1.0726. Min Range: -1.0726

Max Act: 0.8983. Min Act: -0.0000

Data Index: 870754 (C4 (Web Text))

Max Activating Token Index: 870

Text #16

Max Range: 1.0726. Min Range: -1.0726

Max Act: 0.9202. Min Act: -0.0000

Data Index: 861269 (C4 (Web Text))

Max Activating Token Index: 980

Text #17

Max Range: 1.0726. Min Range: -1.0726

Max Act: 0.7658. Min Act: -0.0000

Data Index: 830635 (C4 (Web Text))

Max Activating Token Index: 231

Text #18

Max Range: 1.0726. Min Range: -1.0726

Max Act: 0.9086. Min Act: -0.0000

Data Index: 1418408 (Python Code)

Max Activating Token Index: 442

Text #19

Max Range: 1.0726. Min Range: -1.0726

Max Act: 0.9068. Min Act: -0.0000

Data Index: 1170618 (C4 (Web Text))

Max Activating Token Index: 961