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

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

Neuron 546 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: 3.3500. Min Range: -3.3500

Max Act: 3.3500. Min Act: -0.0000

Data Index: 196750 (C4 (Web Text))

Max Activating Token Index: 619

Text #1

Max Range: 3.3500. Min Range: -3.3500

Max Act: 3.0806. Min Act: -0.0000

Data Index: 1240741 (C4 (Web Text))

Max Activating Token Index: 669

Text #2

Max Range: 3.3500. Min Range: -3.3500

Max Act: 2.6142. Min Act: -0.0001

Data Index: 248749 (C4 (Web Text))

Max Activating Token Index: 183

Text #3

Max Range: 3.3500. Min Range: -3.3500

Max Act: 2.2703. Min Act: -0.0000

Data Index: 1137391 (C4 (Web Text))

Max Activating Token Index: 327

Text #4

Max Range: 3.3500. Min Range: -3.3500

Max Act: 2.4938. Min Act: -0.0000

Data Index: 861991 (C4 (Web Text))

Max Activating Token Index: 891

Text #5

Max Range: 3.3500. Min Range: -3.3500

Max Act: 2.4855. Min Act: -0.0000

Data Index: 247806 (C4 (Web Text))

Max Activating Token Index: 992

Text #6

Max Range: 3.3500. Min Range: -3.3500

Max Act: 2.3553. Min Act: -0.0000

Data Index: 361744 (C4 (Web Text))

Max Activating Token Index: 894

Text #7

Max Range: 3.3500. Min Range: -3.3500

Max Act: 2.4688. Min Act: -0.0000

Data Index: 617234 (C4 (Web Text))

Max Activating Token Index: 188

Text #8

Max Range: 3.3500. Min Range: -3.3500

Max Act: 2.5307. Min Act: -0.0000

Data Index: 892109 (C4 (Web Text))

Max Activating Token Index: 576

Text #9

Max Range: 3.3500. Min Range: -3.3500

Max Act: 2.4946. Min Act: -0.0000

Data Index: 656283 (C4 (Web Text))

Max Activating Token Index: 1001

Text #10

Max Range: 3.3500. Min Range: -3.3500

Max Act: 2.2536. Min Act: -0.0000

Data Index: 1176421 (C4 (Web Text))

Max Activating Token Index: 950

Text #11

Max Range: 3.3500. Min Range: -3.3500

Max Act: 2.2355. Min Act: -0.0000

Data Index: 825368 (C4 (Web Text))

Max Activating Token Index: 548

Text #12

Max Range: 3.3500. Min Range: -3.3500

Max Act: 2.4781. Min Act: -0.0000

Data Index: 845893 (C4 (Web Text))

Max Activating Token Index: 988

Text #13

Max Range: 3.3500. Min Range: -3.3500

Max Act: 2.1680. Min Act: -0.0000

Data Index: 437097 (C4 (Web Text))

Max Activating Token Index: 543

Text #14

Max Range: 3.3500. Min Range: -3.3500

Max Act: 2.1809. Min Act: -0.0001

Data Index: 1241153 (C4 (Web Text))

Max Activating Token Index: 747

Text #15

Max Range: 3.3500. Min Range: -3.3500

Max Act: 2.1630. Min Act: -0.0000

Data Index: 1198141 (C4 (Web Text))

Max Activating Token Index: 55

Text #16

Max Range: 3.3500. Min Range: -3.3500

Max Act: 2.1405. Min Act: -0.0000

Data Index: 399219 (C4 (Web Text))

Max Activating Token Index: 86

Text #17

Max Range: 3.3500. Min Range: -3.3500

Max Act: 2.1093. Min Act: -0.0001

Data Index: 272317 (C4 (Web Text))

Max Activating Token Index: 294

Text #18

Max Range: 3.3500. Min Range: -3.3500

Max Act: 2.3209. Min Act: -0.0000

Data Index: 213473 (C4 (Web Text))

Max Activating Token Index: 39

Text #19

Max Range: 3.3500. Min Range: -3.3500

Max Act: 2.1854. Min Act: -0.0000

Data Index: 165578 (C4 (Web Text))

Max Activating Token Index: 507