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

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

Neuron 4487 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: 2.1072. Min Range: -2.1072

Max Act: 2.1072. Min Act: -0.0000

Data Index: 775762 (C4 (Web Text))

Max Activating Token Index: 97

Text #1

Max Range: 2.1072. Min Range: -2.1072

Max Act: 1.8560. Min Act: 0.0000

Data Index: 565914 (C4 (Web Text))

Max Activating Token Index: 505

Text #2

Max Range: 2.1072. Min Range: -2.1072

Max Act: 1.9416. Min Act: -0.0000

Data Index: 609113 (C4 (Web Text))

Max Activating Token Index: 928

Text #3

Max Range: 2.1072. Min Range: -2.1072

Max Act: 1.6626. Min Act: -0.0000

Data Index: 1295517 (C4 (Web Text))

Max Activating Token Index: 939

Text #4

Max Range: 2.1072. Min Range: -2.1072

Max Act: 1.6311. Min Act: -0.0000

Data Index: 146209 (C4 (Web Text))

Max Activating Token Index: 874

Text #5

Max Range: 2.1072. Min Range: -2.1072

Max Act: 1.5301. Min Act: -0.0000

Data Index: 803892 (C4 (Web Text))

Max Activating Token Index: 404

Text #6

Max Range: 2.1072. Min Range: -2.1072

Max Act: 1.3449. Min Act: -0.0000

Data Index: 722012 (C4 (Web Text))

Max Activating Token Index: 1005

Text #7

Max Range: 2.1072. Min Range: -2.1072

Max Act: 1.3657. Min Act: -0.0000

Data Index: 970148 (C4 (Web Text))

Max Activating Token Index: 415

Text #8

Max Range: 2.1072. Min Range: -2.1072

Max Act: 1.3808. Min Act: -0.0000

Data Index: 470447 (C4 (Web Text))

Max Activating Token Index: 370

Text #9

Max Range: 2.1072. Min Range: -2.1072

Max Act: 1.3196. Min Act: -0.0000

Data Index: 778631 (C4 (Web Text))

Max Activating Token Index: 357

Text #10

Max Range: 2.1072. Min Range: -2.1072

Max Act: 1.2339. Min Act: -0.0000

Data Index: 86286 (C4 (Web Text))

Max Activating Token Index: 1004

Text #11

Max Range: 2.1072. Min Range: -2.1072

Max Act: 1.0981. Min Act: -0.0000

Data Index: 1163157 (C4 (Web Text))

Max Activating Token Index: 256

Text #12

Max Range: 2.1072. Min Range: -2.1072

Max Act: 1.0839. Min Act: -0.0000

Data Index: 427490 (C4 (Web Text))

Max Activating Token Index: 701

Text #13

Max Range: 2.1072. Min Range: -2.1072

Max Act: 1.3138. Min Act: -0.0000

Data Index: 194064 (C4 (Web Text))

Max Activating Token Index: 51

Text #14

Max Range: 2.1072. Min Range: -2.1072

Max Act: 1.3263. Min Act: -0.0000

Data Index: 1309900 (C4 (Web Text))

Max Activating Token Index: 928

Text #15

Max Range: 2.1072. Min Range: -2.1072

Max Act: 1.1692. Min Act: -0.0000

Data Index: 1270955 (C4 (Web Text))

Max Activating Token Index: 398

Text #16

Max Range: 2.1072. Min Range: -2.1072

Max Act: 1.1817. Min Act: -0.0000

Data Index: 1042007 (C4 (Web Text))

Max Activating Token Index: 899

Text #17

Max Range: 2.1072. Min Range: -2.1072

Max Act: 1.1636. Min Act: -0.0000

Data Index: 802501 (C4 (Web Text))

Max Activating Token Index: 599

Text #18

Max Range: 2.1072. Min Range: -2.1072

Max Act: 1.2080. Min Act: -0.0000

Data Index: 707821 (C4 (Web Text))

Max Activating Token Index: 471

Text #19

Max Range: 2.1072. Min Range: -2.1072

Max Act: 1.0887. Min Act: -0.0000

Data Index: 104908 (C4 (Web Text))

Max Activating Token Index: 254