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

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

Neuron 509 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.2809. Min Range: -4.2809

Max Act: 4.2809. Min Act: -0.0000

Data Index: 692658 (C4 (Web Text))

Max Activating Token Index: 162

Text #1

Max Range: 4.2809. Min Range: -4.2809

Max Act: 3.6981. Min Act: -0.0000

Data Index: 529679 (C4 (Web Text))

Max Activating Token Index: 232

Text #2

Max Range: 4.2809. Min Range: -4.2809

Max Act: 3.6280. Min Act: -0.0000

Data Index: 1191231 (C4 (Web Text))

Max Activating Token Index: 16

Text #3

Max Range: 4.2809. Min Range: -4.2809

Max Act: 3.7379. Min Act: -0.0000

Data Index: 291716 (C4 (Web Text))

Max Activating Token Index: 566

Text #4

Max Range: 4.2809. Min Range: -4.2809

Max Act: 3.7072. Min Act: -0.0000

Data Index: 752474 (C4 (Web Text))

Max Activating Token Index: 754

Text #5

Max Range: 4.2809. Min Range: -4.2809

Max Act: 3.5091. Min Act: -0.0000

Data Index: 721931 (C4 (Web Text))

Max Activating Token Index: 782

Text #6

Max Range: 4.2809. Min Range: -4.2809

Max Act: 3.6435. Min Act: -0.0000

Data Index: 1338049 (C4 (Web Text))

Max Activating Token Index: 68

Text #7

Max Range: 4.2809. Min Range: -4.2809

Max Act: 3.5818. Min Act: -0.0000

Data Index: 1144074 (C4 (Web Text))

Max Activating Token Index: 543

Text #8

Max Range: 4.2809. Min Range: -4.2809

Max Act: 3.4412. Min Act: -0.0000

Data Index: 509942 (C4 (Web Text))

Max Activating Token Index: 716

Text #9

Max Range: 4.2809. Min Range: -4.2809

Max Act: 3.4159. Min Act: -0.0000

Data Index: 57399 (C4 (Web Text))

Max Activating Token Index: 184

Text #10

Max Range: 4.2809. Min Range: -4.2809

Max Act: 3.4248. Min Act: -0.0000

Data Index: 86840 (C4 (Web Text))

Max Activating Token Index: 858

Text #11

Max Range: 4.2809. Min Range: -4.2809

Max Act: 3.5476. Min Act: -0.0000

Data Index: 1240868 (C4 (Web Text))

Max Activating Token Index: 489

Text #12

Max Range: 4.2809. Min Range: -4.2809

Max Act: 3.5369. Min Act: -0.0000

Data Index: 446745 (C4 (Web Text))

Max Activating Token Index: 875

Text #13

Max Range: 4.2809. Min Range: -4.2809

Max Act: 3.3755. Min Act: -0.0000

Data Index: 1090658 (C4 (Web Text))

Max Activating Token Index: 189

Text #14

Max Range: 4.2809. Min Range: -4.2809

Max Act: 3.3670. Min Act: -0.0000

Data Index: 554717 (C4 (Web Text))

Max Activating Token Index: 594

Text #15

Max Range: 4.2809. Min Range: -4.2809

Max Act: 3.3132. Min Act: -0.0000

Data Index: 346285 (C4 (Web Text))

Max Activating Token Index: 508

Text #16

Max Range: 4.2809. Min Range: -4.2809

Max Act: 3.4418. Min Act: -0.0000

Data Index: 1026512 (C4 (Web Text))

Max Activating Token Index: 826

Text #17

Max Range: 4.2809. Min Range: -4.2809

Max Act: 3.4299. Min Act: -0.0000

Data Index: 1025907 (C4 (Web Text))

Max Activating Token Index: 956

Text #18

Max Range: 4.2809. Min Range: -4.2809

Max Act: 3.4282. Min Act: -0.0000

Data Index: 1210131 (C4 (Web Text))

Max Activating Token Index: 837

Text #19

Max Range: 4.2809. Min Range: -4.2809

Max Act: 3.5731. Min Act: -0.0000

Data Index: 1100175 (C4 (Web Text))

Max Activating Token Index: 952