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

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

Neuron 1785 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: 0.8425. Min Range: -0.8425

Max Act: 0.8425. Min Act: -0.0001

Data Index: 713553 (C4 (Web Text))

Max Activating Token Index: 863

Text #1

Max Range: 0.8425. Min Range: -0.8425

Max Act: 0.7796. Min Act: -0.0001

Data Index: 963296 (C4 (Web Text))

Max Activating Token Index: 462

Text #2

Max Range: 0.8425. Min Range: -0.8425

Max Act: 0.7563. Min Act: -0.0000

Data Index: 656560 (C4 (Web Text))

Max Activating Token Index: 827

Text #3

Max Range: 0.8425. Min Range: -0.8425

Max Act: 0.6743. Min Act: -0.0001

Data Index: 86245 (C4 (Web Text))

Max Activating Token Index: 694

Text #4

Max Range: 0.8425. Min Range: -0.8425

Max Act: 0.6668. Min Act: -0.0001

Data Index: 951265 (C4 (Web Text))

Max Activating Token Index: 87

Text #5

Max Range: 0.8425. Min Range: -0.8425

Max Act: 0.6049. Min Act: -0.0000

Data Index: 1213795 (C4 (Web Text))

Max Activating Token Index: 336

Text #6

Max Range: 0.8425. Min Range: -0.8425

Max Act: 0.6453. Min Act: -0.0000

Data Index: 992632 (C4 (Web Text))

Max Activating Token Index: 190

Text #7

Max Range: 0.8425. Min Range: -0.8425

Max Act: 0.6156. Min Act: -0.0000

Data Index: 789762 (C4 (Web Text))

Max Activating Token Index: 899

Text #8

Max Range: 0.8425. Min Range: -0.8425

Max Act: 0.6171. Min Act: -0.0001

Data Index: 974700 (C4 (Web Text))

Max Activating Token Index: 132

Text #9

Max Range: 0.8425. Min Range: -0.8425

Max Act: 0.6092. Min Act: -0.0000

Data Index: 494770 (C4 (Web Text))

Max Activating Token Index: 221

Text #10

Max Range: 0.8425. Min Range: -0.8425

Max Act: 0.6457. Min Act: -0.0001

Data Index: 822924 (C4 (Web Text))

Max Activating Token Index: 549

Text #11

Max Range: 0.8425. Min Range: -0.8425

Max Act: 0.5993. Min Act: -0.0000

Data Index: 693665 (C4 (Web Text))

Max Activating Token Index: 199

Text #12

Max Range: 0.8425. Min Range: -0.8425

Max Act: 0.6258. Min Act: -0.0001

Data Index: 578055 (C4 (Web Text))

Max Activating Token Index: 166

Text #13

Max Range: 0.8425. Min Range: -0.8425

Max Act: 0.6053. Min Act: -0.0001

Data Index: 1109513 (C4 (Web Text))

Max Activating Token Index: 357

Text #14

Max Range: 0.8425. Min Range: -0.8425

Max Act: 0.5822. Min Act: -0.0001

Data Index: 185452 (C4 (Web Text))

Max Activating Token Index: 522

Text #15

Max Range: 0.8425. Min Range: -0.8425

Max Act: 0.6019. Min Act: -0.0001

Data Index: 700867 (C4 (Web Text))

Max Activating Token Index: 490

Text #16

Max Range: 0.8425. Min Range: -0.8425

Max Act: 0.5595. Min Act: -0.0001

Data Index: 1166873 (C4 (Web Text))

Max Activating Token Index: 585

Text #17

Max Range: 0.8425. Min Range: -0.8425

Max Act: 0.6138. Min Act: -0.0001

Data Index: 859895 (C4 (Web Text))

Max Activating Token Index: 145

Text #18

Max Range: 0.8425. Min Range: -0.8425

Max Act: 0.5862. Min Act: -0.0001

Data Index: 706496 (C4 (Web Text))

Max Activating Token Index: 629

Text #19

Max Range: 0.8425. Min Range: -0.8425

Max Act: 0.5474. Min Act: -0.0000

Data Index: 981796 (C4 (Web Text))

Max Activating Token Index: 325