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

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

Neuron 3380 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5795. Min Range: -0.5795

Max Act: 0.5795. Min Act: -0.0000

Data Index: 887213 (C4 (Web Text))

Max Activating Token Index: 732

Text #1

Max Range: 0.5795. Min Range: -0.5795

Max Act: 0.5742. Min Act: -0.0000

Data Index: 137071 (C4 (Web Text))

Max Activating Token Index: 931

Text #2

Max Range: 0.5795. Min Range: -0.5795

Max Act: 0.5747. Min Act: -0.0000

Data Index: 925097 (C4 (Web Text))

Max Activating Token Index: 949

Text #3

Max Range: 0.5795. Min Range: -0.5795

Max Act: 0.4871. Min Act: -0.0000

Data Index: 974311 (C4 (Web Text))

Max Activating Token Index: 204

Text #4

Max Range: 0.5795. Min Range: -0.5795

Max Act: 0.5181. Min Act: -0.0000

Data Index: 1146509 (C4 (Web Text))

Max Activating Token Index: 138

Text #5

Max Range: 0.5795. Min Range: -0.5795

Max Act: 0.5280. Min Act: -0.0000

Data Index: 1184618 (C4 (Web Text))

Max Activating Token Index: 317

Text #6

Max Range: 0.5795. Min Range: -0.5795

Max Act: 0.5399. Min Act: -0.0000

Data Index: 1163232 (C4 (Web Text))

Max Activating Token Index: 673

Text #7

Max Range: 0.5795. Min Range: -0.5795

Max Act: 0.4877. Min Act: -0.0000

Data Index: 459821 (C4 (Web Text))

Max Activating Token Index: 199

Text #8

Max Range: 0.5795. Min Range: -0.5795

Max Act: 0.5495. Min Act: -0.0000

Data Index: 291803 (C4 (Web Text))

Max Activating Token Index: 824

Text #9

Max Range: 0.5795. Min Range: -0.5795

Max Act: 0.5330. Min Act: -0.0000

Data Index: 770373 (C4 (Web Text))

Max Activating Token Index: 936

Text #10

Max Range: 0.5795. Min Range: -0.5795

Max Act: 0.5248. Min Act: -0.0000

Data Index: 1205969 (C4 (Web Text))

Max Activating Token Index: 486

Text #11

Max Range: 0.5795. Min Range: -0.5795

Max Act: 0.4813. Min Act: -0.0000

Data Index: 874968 (C4 (Web Text))

Max Activating Token Index: 573

Text #12

Max Range: 0.5795. Min Range: -0.5795

Max Act: 0.5053. Min Act: -0.0000

Data Index: 227385 (C4 (Web Text))

Max Activating Token Index: 938

Text #13

Max Range: 0.5795. Min Range: -0.5795

Max Act: 0.4352. Min Act: -0.0000

Data Index: 427536 (C4 (Web Text))

Max Activating Token Index: 134

Text #14

Max Range: 0.5795. Min Range: -0.5795

Max Act: 0.4643. Min Act: -0.0000

Data Index: 368903 (C4 (Web Text))

Max Activating Token Index: 640

Text #15

Max Range: 0.5795. Min Range: -0.5795

Max Act: 0.4170. Min Act: -0.0000

Data Index: 428024 (C4 (Web Text))

Max Activating Token Index: 687

Text #16

Max Range: 0.5795. Min Range: -0.5795

Max Act: 0.4243. Min Act: -0.0000

Data Index: 603886 (C4 (Web Text))

Max Activating Token Index: 345

Text #17

Max Range: 0.5795. Min Range: -0.5795

Max Act: 0.4301. Min Act: -0.0000

Data Index: 786216 (C4 (Web Text))

Max Activating Token Index: 1014

Text #18

Max Range: 0.5795. Min Range: -0.5795

Max Act: 0.4498. Min Act: -0.0000

Data Index: 21808 (C4 (Web Text))

Max Activating Token Index: 764

Text #19

Max Range: 0.5795. Min Range: -0.5795

Max Act: 0.4050. Min Act: -0.0000

Data Index: 114499 (C4 (Web Text))

Max Activating Token Index: 858