Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 236 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1199. Min Range: -0.1199

Max Act: 0.1199. Min Act: -0.0000

Data Index: 808473 (C4 (Web Text))

Max Activating Token Index: 156

Text #1

Max Range: 0.1199. Min Range: -0.1199

Max Act: 0.1120. Min Act: -0.0001

Data Index: 144945 (C4 (Web Text))

Max Activating Token Index: 20

Text #2

Max Range: 0.1199. Min Range: -0.1199

Max Act: 0.1124. Min Act: -0.0000

Data Index: 177821 (C4 (Web Text))

Max Activating Token Index: 814

Text #3

Max Range: 0.1199. Min Range: -0.1199

Max Act: 0.1053. Min Act: -0.0001

Data Index: 568256 (C4 (Web Text))

Max Activating Token Index: 221

Text #4

Max Range: 0.1199. Min Range: -0.1199

Max Act: 0.1042. Min Act: -0.0001

Data Index: 953168 (C4 (Web Text))

Max Activating Token Index: 305

Text #5

Max Range: 0.1199. Min Range: -0.1199

Max Act: 0.1069. Min Act: -0.0000

Data Index: 534391 (C4 (Web Text))

Max Activating Token Index: 698

Text #6

Max Range: 0.1199. Min Range: -0.1199

Max Act: 0.0962. Min Act: -0.0000

Data Index: 799298 (C4 (Web Text))

Max Activating Token Index: 400

Text #7

Max Range: 0.1199. Min Range: -0.1199

Max Act: 0.0943. Min Act: -0.0000

Data Index: 442281 (C4 (Web Text))

Max Activating Token Index: 216

Text #8

Max Range: 0.1199. Min Range: -0.1199

Max Act: 0.0899. Min Act: -0.0000

Data Index: 111634 (C4 (Web Text))

Max Activating Token Index: 63

Text #9

Max Range: 0.1199. Min Range: -0.1199

Max Act: 0.0884. Min Act: -0.0001

Data Index: 720710 (C4 (Web Text))

Max Activating Token Index: 570

Text #10

Max Range: 0.1199. Min Range: -0.1199

Max Act: 0.0899. Min Act: -0.0001

Data Index: 215748 (C4 (Web Text))

Max Activating Token Index: 174

Text #11

Max Range: 0.1199. Min Range: -0.1199

Max Act: 0.0929. Min Act: -0.0001

Data Index: 847183 (C4 (Web Text))

Max Activating Token Index: 922

Text #12

Max Range: 0.1199. Min Range: -0.1199

Max Act: 0.0892. Min Act: -0.0001

Data Index: 940195 (C4 (Web Text))

Max Activating Token Index: 899

Text #13

Max Range: 0.1199. Min Range: -0.1199

Max Act: 0.0851. Min Act: -0.0000

Data Index: 666885 (C4 (Web Text))

Max Activating Token Index: 319

Text #14

Max Range: 0.1199. Min Range: -0.1199

Max Act: 0.0878. Min Act: -0.0001

Data Index: 108352 (C4 (Web Text))

Max Activating Token Index: 345

Text #15

Max Range: 0.1199. Min Range: -0.1199

Max Act: 0.0808. Min Act: -0.0000

Data Index: 1100466 (C4 (Web Text))

Max Activating Token Index: 585

Text #16

Max Range: 0.1199. Min Range: -0.1199

Max Act: 0.0807. Min Act: -0.0000

Data Index: 330797 (C4 (Web Text))

Max Activating Token Index: 987

Text #17

Max Range: 0.1199. Min Range: -0.1199

Max Act: 0.0847. Min Act: -0.0000

Data Index: 571771 (C4 (Web Text))

Max Activating Token Index: 778

Text #18

Max Range: 0.1199. Min Range: -0.1199

Max Act: 0.0879. Min Act: -0.0000

Data Index: 1179695 (C4 (Web Text))

Max Activating Token Index: 515

Text #19

Max Range: 0.1199. Min Range: -0.1199

Max Act: 0.0847. Min Act: -0.0000

Data Index: 673786 (C4 (Web Text))

Max Activating Token Index: 561