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

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

Neuron 4071 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6563. Min Range: -0.6563

Max Act: 0.6402. Min Act: -0.0001

Data Index: 289779 (C4 (Web Text))

Max Activating Token Index: 55

Text #1

Max Range: 0.6563. Min Range: -0.6563

Max Act: 0.6563. Min Act: -0.0000

Data Index: 126221 (C4 (Web Text))

Max Activating Token Index: 74

Text #2

Max Range: 0.6563. Min Range: -0.6563

Max Act: 0.5860. Min Act: -0.0001

Data Index: 1038136 (C4 (Web Text))

Max Activating Token Index: 573

Text #3

Max Range: 0.6563. Min Range: -0.6563

Max Act: 0.5800. Min Act: -0.0000

Data Index: 316864 (C4 (Web Text))

Max Activating Token Index: 523

Text #4

Max Range: 0.6563. Min Range: -0.6563

Max Act: 0.5137. Min Act: -0.0001

Data Index: 1221025 (C4 (Web Text))

Max Activating Token Index: 690

Text #5

Max Range: 0.6563. Min Range: -0.6563

Max Act: 0.4939. Min Act: -0.0000

Data Index: 1192053 (C4 (Web Text))

Max Activating Token Index: 341

Text #6

Max Range: 0.6563. Min Range: -0.6563

Max Act: 0.4783. Min Act: -0.0000

Data Index: 833270 (C4 (Web Text))

Max Activating Token Index: 1008

Text #7

Max Range: 0.6563. Min Range: -0.6563

Max Act: 0.4524. Min Act: -0.0000

Data Index: 1329286 (C4 (Web Text))

Max Activating Token Index: 656

Text #8

Max Range: 0.6563. Min Range: -0.6563

Max Act: 0.4137. Min Act: -0.0000

Data Index: 401745 (C4 (Web Text))

Max Activating Token Index: 1022

Text #9

Max Range: 0.6563. Min Range: -0.6563

Max Act: 0.4010. Min Act: -0.0000

Data Index: 765173 (C4 (Web Text))

Max Activating Token Index: 752

Text #10

Max Range: 0.6563. Min Range: -0.6563

Max Act: 0.4438. Min Act: -0.0001

Data Index: 684593 (C4 (Web Text))

Max Activating Token Index: 580

Text #11

Max Range: 0.6563. Min Range: -0.6563

Max Act: 0.4166. Min Act: -0.0000

Data Index: 921285 (C4 (Web Text))

Max Activating Token Index: 1021

Text #12

Max Range: 0.6563. Min Range: -0.6563

Max Act: 0.4157. Min Act: -0.0001

Data Index: 270648 (C4 (Web Text))

Max Activating Token Index: 260

Text #13

Max Range: 0.6563. Min Range: -0.6563

Max Act: 0.4155. Min Act: -0.0001

Data Index: 55932 (C4 (Web Text))

Max Activating Token Index: 925

Text #14

Max Range: 0.6563. Min Range: -0.6563

Max Act: 0.4006. Min Act: -0.0001

Data Index: 144791 (C4 (Web Text))

Max Activating Token Index: 285

Text #15

Max Range: 0.6563. Min Range: -0.6563

Max Act: 0.4115. Min Act: -0.0000

Data Index: 794632 (C4 (Web Text))

Max Activating Token Index: 434

Text #16

Max Range: 0.6563. Min Range: -0.6563

Max Act: 0.4096. Min Act: -0.0001

Data Index: 1256034 (C4 (Web Text))

Max Activating Token Index: 168

Text #17

Max Range: 0.6563. Min Range: -0.6563

Max Act: 0.4243. Min Act: -0.0000

Data Index: 539852 (C4 (Web Text))

Max Activating Token Index: 472

Text #18

Max Range: 0.6563. Min Range: -0.6563

Max Act: 0.4023. Min Act: -0.0000

Data Index: 830156 (C4 (Web Text))

Max Activating Token Index: 438

Text #19

Max Range: 0.6563. Min Range: -0.6563

Max Act: 0.4002. Min Act: -0.0000

Data Index: 90636 (C4 (Web Text))

Max Activating Token Index: 428