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

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

Neuron 3244 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5877. Min Range: -1.5877

Max Act: 1.5877. Min Act: -0.0001

Data Index: 347201 (C4 (Web Text))

Max Activating Token Index: 769

Text #1

Max Range: 1.5877. Min Range: -1.5877

Max Act: 1.3781. Min Act: -0.0001

Data Index: 549715 (C4 (Web Text))

Max Activating Token Index: 333

Text #2

Max Range: 1.5877. Min Range: -1.5877

Max Act: 1.3177. Min Act: -0.0001

Data Index: 1179827 (C4 (Web Text))

Max Activating Token Index: 662

Text #3

Max Range: 1.5877. Min Range: -1.5877

Max Act: 1.2362. Min Act: -0.0001

Data Index: 292915 (C4 (Web Text))

Max Activating Token Index: 266

Text #4

Max Range: 1.5877. Min Range: -1.5877

Max Act: 1.2715. Min Act: -0.0001

Data Index: 388214 (C4 (Web Text))

Max Activating Token Index: 598

Text #5

Max Range: 1.5877. Min Range: -1.5877

Max Act: 1.1814. Min Act: -0.0001

Data Index: 403144 (C4 (Web Text))

Max Activating Token Index: 284

Text #6

Max Range: 1.5877. Min Range: -1.5877

Max Act: 1.2249. Min Act: -0.0001

Data Index: 1001671 (C4 (Web Text))

Max Activating Token Index: 65

Text #7

Max Range: 1.5877. Min Range: -1.5877

Max Act: 1.1743. Min Act: -0.0001

Data Index: 1305226 (C4 (Web Text))

Max Activating Token Index: 202

Text #8

Max Range: 1.5877. Min Range: -1.5877

Max Act: 1.1357. Min Act: -0.0001

Data Index: 1179845 (C4 (Web Text))

Max Activating Token Index: 221

Text #9

Max Range: 1.5877. Min Range: -1.5877

Max Act: 1.1331. Min Act: -0.0001

Data Index: 456852 (C4 (Web Text))

Max Activating Token Index: 619

Text #10

Max Range: 1.5877. Min Range: -1.5877

Max Act: 1.1096. Min Act: -0.0001

Data Index: 839015 (C4 (Web Text))

Max Activating Token Index: 760

Text #11

Max Range: 1.5877. Min Range: -1.5877

Max Act: 1.1697. Min Act: -0.0001

Data Index: 304566 (C4 (Web Text))

Max Activating Token Index: 180

Text #12

Max Range: 1.5877. Min Range: -1.5877

Max Act: 1.0900. Min Act: -0.0001

Data Index: 448714 (C4 (Web Text))

Max Activating Token Index: 727

Text #13

Max Range: 1.5877. Min Range: -1.5877

Max Act: 1.0898. Min Act: -0.0001

Data Index: 866074 (C4 (Web Text))

Max Activating Token Index: 446

Text #14

Max Range: 1.5877. Min Range: -1.5877

Max Act: 1.0824. Min Act: -0.0001

Data Index: 695676 (C4 (Web Text))

Max Activating Token Index: 606

Text #15

Max Range: 1.5877. Min Range: -1.5877

Max Act: 1.1426. Min Act: -0.0001

Data Index: 854124 (C4 (Web Text))

Max Activating Token Index: 459

Text #16

Max Range: 1.5877. Min Range: -1.5877

Max Act: 1.1169. Min Act: -0.0001

Data Index: 258745 (C4 (Web Text))

Max Activating Token Index: 931

Text #17

Max Range: 1.5877. Min Range: -1.5877

Max Act: 1.1091. Min Act: -0.0001

Data Index: 427289 (C4 (Web Text))

Max Activating Token Index: 467

Text #18

Max Range: 1.5877. Min Range: -1.5877

Max Act: 1.0848. Min Act: -0.0001

Data Index: 324639 (C4 (Web Text))

Max Activating Token Index: 884

Text #19

Max Range: 1.5877. Min Range: -1.5877

Max Act: 1.0895. Min Act: -0.0001

Data Index: 126805 (C4 (Web Text))

Max Activating Token Index: 483