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

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

Neuron 4560 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4140. Min Range: -2.4140

Max Act: 2.4140. Min Act: -0.0000

Data Index: 215486 (C4 (Web Text))

Max Activating Token Index: 211

Text #1

Max Range: 2.4140. Min Range: -2.4140

Max Act: 1.7562. Min Act: -0.0000

Data Index: 33272 (C4 (Web Text))

Max Activating Token Index: 283

Text #2

Max Range: 2.4140. Min Range: -2.4140

Max Act: 1.5420. Min Act: -0.0000

Data Index: 853267 (C4 (Web Text))

Max Activating Token Index: 628

Text #3

Max Range: 2.4140. Min Range: -2.4140

Max Act: 1.5244. Min Act: -0.0000

Data Index: 594867 (C4 (Web Text))

Max Activating Token Index: 944

Text #4

Max Range: 2.4140. Min Range: -2.4140

Max Act: 1.5057. Min Act: -0.0000

Data Index: 1044382 (C4 (Web Text))

Max Activating Token Index: 822

Text #5

Max Range: 2.4140. Min Range: -2.4140

Max Act: 1.4119. Min Act: -0.0000

Data Index: 20149 (C4 (Web Text))

Max Activating Token Index: 489

Text #6

Max Range: 2.4140. Min Range: -2.4140

Max Act: 1.4652. Min Act: -0.0000

Data Index: 35167 (C4 (Web Text))

Max Activating Token Index: 929

Text #7

Max Range: 2.4140. Min Range: -2.4140

Max Act: 1.4659. Min Act: -0.0000

Data Index: 992342 (C4 (Web Text))

Max Activating Token Index: 634

Text #8

Max Range: 2.4140. Min Range: -2.4140

Max Act: 1.4524. Min Act: -0.0000

Data Index: 1295006 (C4 (Web Text))

Max Activating Token Index: 1008

Text #9

Max Range: 2.4140. Min Range: -2.4140

Max Act: 1.3615. Min Act: -0.0000

Data Index: 817639 (C4 (Web Text))

Max Activating Token Index: 899

Text #10

Max Range: 2.4140. Min Range: -2.4140

Max Act: 1.3611. Min Act: -0.0000

Data Index: 472321 (C4 (Web Text))

Max Activating Token Index: 190

Text #11

Max Range: 2.4140. Min Range: -2.4140

Max Act: 1.2869. Min Act: -0.0000

Data Index: 506659 (C4 (Web Text))

Max Activating Token Index: 917

Text #12

Max Range: 2.4140. Min Range: -2.4140

Max Act: 1.4163. Min Act: -0.0000

Data Index: 225348 (C4 (Web Text))

Max Activating Token Index: 164

Text #13

Max Range: 2.4140. Min Range: -2.4140

Max Act: 1.3152. Min Act: -0.0000

Data Index: 696530 (C4 (Web Text))

Max Activating Token Index: 797

Text #14

Max Range: 2.4140. Min Range: -2.4140

Max Act: 1.3195. Min Act: -0.0000

Data Index: 650518 (C4 (Web Text))

Max Activating Token Index: 309

Text #15

Max Range: 2.4140. Min Range: -2.4140

Max Act: 1.3061. Min Act: -0.0000

Data Index: 1328309 (C4 (Web Text))

Max Activating Token Index: 1007

Text #16

Max Range: 2.4140. Min Range: -2.4140

Max Act: 1.2824. Min Act: -0.0000

Data Index: 77136 (C4 (Web Text))

Max Activating Token Index: 857

Text #17

Max Range: 2.4140. Min Range: -2.4140

Max Act: 1.3553. Min Act: -0.0000

Data Index: 1352306 (C4 (Web Text))

Max Activating Token Index: 829

Text #18

Max Range: 2.4140. Min Range: -2.4140

Max Act: 1.2942. Min Act: -0.0000

Data Index: 125907 (C4 (Web Text))

Max Activating Token Index: 551

Text #19

Max Range: 2.4140. Min Range: -2.4140

Max Act: 1.2850. Min Act: -0.0000

Data Index: 889032 (C4 (Web Text))

Max Activating Token Index: 492