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

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

Neuron 3725 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9728. Min Range: -1.9728

Max Act: 1.8122. Min Act: -0.0001

Data Index: 868523 (C4 (Web Text))

Max Activating Token Index: 570

Text #1

Max Range: 1.9728. Min Range: -1.9728

Max Act: 1.9728. Min Act: -0.0001

Data Index: 726422 (C4 (Web Text))

Max Activating Token Index: 137

Text #2

Max Range: 1.9728. Min Range: -1.9728

Max Act: 1.7805. Min Act: -0.0001

Data Index: 730212 (C4 (Web Text))

Max Activating Token Index: 107

Text #3

Max Range: 1.9728. Min Range: -1.9728

Max Act: 1.7053. Min Act: -0.0001

Data Index: 890323 (C4 (Web Text))

Max Activating Token Index: 969

Text #4

Max Range: 1.9728. Min Range: -1.9728

Max Act: 1.8497. Min Act: -0.0001

Data Index: 417962 (C4 (Web Text))

Max Activating Token Index: 643

Text #5

Max Range: 1.9728. Min Range: -1.9728

Max Act: 1.7857. Min Act: -0.0001

Data Index: 270040 (C4 (Web Text))

Max Activating Token Index: 487

Text #6

Max Range: 1.9728. Min Range: -1.9728

Max Act: 1.7385. Min Act: -0.0001

Data Index: 155920 (C4 (Web Text))

Max Activating Token Index: 190

Text #7

Max Range: 1.9728. Min Range: -1.9728

Max Act: 1.8117. Min Act: -0.0001

Data Index: 1267072 (C4 (Web Text))

Max Activating Token Index: 835

Text #8

Max Range: 1.9728. Min Range: -1.9728

Max Act: 1.7483. Min Act: -0.0001

Data Index: 754029 (C4 (Web Text))

Max Activating Token Index: 435

Text #9

Max Range: 1.9728. Min Range: -1.9728

Max Act: 1.6545. Min Act: -0.0001

Data Index: 1091143 (C4 (Web Text))

Max Activating Token Index: 628

Text #10

Max Range: 1.9728. Min Range: -1.9728

Max Act: 1.6984. Min Act: -0.0001

Data Index: 908668 (C4 (Web Text))

Max Activating Token Index: 420

Text #11

Max Range: 1.9728. Min Range: -1.9728

Max Act: 1.7439. Min Act: -0.0001

Data Index: 696891 (C4 (Web Text))

Max Activating Token Index: 333

Text #12

Max Range: 1.9728. Min Range: -1.9728

Max Act: 1.5937. Min Act: -0.0001

Data Index: 216913 (C4 (Web Text))

Max Activating Token Index: 157

Text #13

Max Range: 1.9728. Min Range: -1.9728

Max Act: 1.7174. Min Act: -0.0001

Data Index: 976141 (C4 (Web Text))

Max Activating Token Index: 583

Text #14

Max Range: 1.9728. Min Range: -1.9728

Max Act: 1.7288. Min Act: -0.0001

Data Index: 411579 (C4 (Web Text))

Max Activating Token Index: 729

Text #15

Max Range: 1.9728. Min Range: -1.9728

Max Act: 1.5745. Min Act: -0.0001

Data Index: 34131 (C4 (Web Text))

Max Activating Token Index: 796

Text #16

Max Range: 1.9728. Min Range: -1.9728

Max Act: 1.7272. Min Act: -0.0001

Data Index: 757778 (C4 (Web Text))

Max Activating Token Index: 923

Text #17

Max Range: 1.9728. Min Range: -1.9728

Max Act: 1.5720. Min Act: -0.0001

Data Index: 578289 (C4 (Web Text))

Max Activating Token Index: 113

Text #18

Max Range: 1.9728. Min Range: -1.9728

Max Act: 1.6193. Min Act: -0.0001

Data Index: 1138432 (C4 (Web Text))

Max Activating Token Index: 430

Text #19

Max Range: 1.9728. Min Range: -1.9728

Max Act: 1.5589. Min Act: -0.0001

Data Index: 634554 (C4 (Web Text))

Max Activating Token Index: 219