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

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

Neuron 3927 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.1189. Min Range: -2.1189

Max Act: 2.1189. Min Act: -0.0000

Data Index: 407201 (C4 (Web Text))

Max Activating Token Index: 535

Text #1

Max Range: 2.1189. Min Range: -2.1189

Max Act: 2.0005. Min Act: -0.0000

Data Index: 330025 (C4 (Web Text))

Max Activating Token Index: 225

Text #2

Max Range: 2.1189. Min Range: -2.1189

Max Act: 1.8521. Min Act: -0.0000

Data Index: 747341 (C4 (Web Text))

Max Activating Token Index: 604

Text #3

Max Range: 2.1189. Min Range: -2.1189

Max Act: 1.8420. Min Act: -0.0000

Data Index: 316613 (C4 (Web Text))

Max Activating Token Index: 673

Text #4

Max Range: 2.1189. Min Range: -2.1189

Max Act: 1.8929. Min Act: -0.0000

Data Index: 178206 (C4 (Web Text))

Max Activating Token Index: 312

Text #5

Max Range: 2.1189. Min Range: -2.1189

Max Act: 1.7632. Min Act: -0.0000

Data Index: 578635 (C4 (Web Text))

Max Activating Token Index: 122

Text #6

Max Range: 2.1189. Min Range: -2.1189

Max Act: 1.6406. Min Act: -0.0000

Data Index: 1131175 (C4 (Web Text))

Max Activating Token Index: 795

Text #7

Max Range: 2.1189. Min Range: -2.1189

Max Act: 1.6216. Min Act: -0.0000

Data Index: 572590 (C4 (Web Text))

Max Activating Token Index: 909

Text #8

Max Range: 2.1189. Min Range: -2.1189

Max Act: 1.5877. Min Act: -0.0000

Data Index: 38155 (C4 (Web Text))

Max Activating Token Index: 1007

Text #9

Max Range: 2.1189. Min Range: -2.1189

Max Act: 1.4741. Min Act: -0.0000

Data Index: 345496 (C4 (Web Text))

Max Activating Token Index: 275

Text #10

Max Range: 2.1189. Min Range: -2.1189

Max Act: 1.4917. Min Act: -0.0000

Data Index: 1248078 (C4 (Web Text))

Max Activating Token Index: 230

Text #11

Max Range: 2.1189. Min Range: -2.1189

Max Act: 1.4756. Min Act: -0.0000

Data Index: 1240933 (C4 (Web Text))

Max Activating Token Index: 181

Text #12

Max Range: 2.1189. Min Range: -2.1189

Max Act: 1.3869. Min Act: -0.0000

Data Index: 1171176 (C4 (Web Text))

Max Activating Token Index: 414

Text #13

Max Range: 2.1189. Min Range: -2.1189

Max Act: 1.5575. Min Act: -0.0000

Data Index: 1269828 (C4 (Web Text))

Max Activating Token Index: 166

Text #14

Max Range: 2.1189. Min Range: -2.1189

Max Act: 1.4621. Min Act: -0.0000

Data Index: 1020419 (C4 (Web Text))

Max Activating Token Index: 963

Text #15

Max Range: 2.1189. Min Range: -2.1189

Max Act: 1.3624. Min Act: -0.0000

Data Index: 33197 (C4 (Web Text))

Max Activating Token Index: 106

Text #16

Max Range: 2.1189. Min Range: -2.1189

Max Act: 1.5360. Min Act: -0.0000

Data Index: 934675 (C4 (Web Text))

Max Activating Token Index: 941

Text #17

Max Range: 2.1189. Min Range: -2.1189

Max Act: 1.4313. Min Act: -0.0000

Data Index: 1096647 (C4 (Web Text))

Max Activating Token Index: 625

Text #18

Max Range: 2.1189. Min Range: -2.1189

Max Act: 1.4381. Min Act: -0.0000

Data Index: 142792 (C4 (Web Text))

Max Activating Token Index: 418

Text #19

Max Range: 2.1189. Min Range: -2.1189

Max Act: 1.4119. Min Act: -0.0000

Data Index: 26135 (C4 (Web Text))

Max Activating Token Index: 1011