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

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

Neuron 1088 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9192. Min Range: -0.9192

Max Act: 0.8561. Min Act: -0.0002

Data Index: 1088353 (C4 (Web Text))

Max Activating Token Index: 55

Text #1

Max Range: 0.9192. Min Range: -0.9192

Max Act: 0.9020. Min Act: -0.0002

Data Index: 898619 (C4 (Web Text))

Max Activating Token Index: 269

Text #2

Max Range: 0.9192. Min Range: -0.9192

Max Act: 0.9192. Min Act: -0.0002

Data Index: 693445 (C4 (Web Text))

Max Activating Token Index: 177

Text #3

Max Range: 0.9192. Min Range: -0.9192

Max Act: 0.8979. Min Act: -0.0002

Data Index: 1153577 (C4 (Web Text))

Max Activating Token Index: 991

Text #4

Max Range: 0.9192. Min Range: -0.9192

Max Act: 0.8720. Min Act: -0.0002

Data Index: 1187179 (C4 (Web Text))

Max Activating Token Index: 548

Text #5

Max Range: 0.9192. Min Range: -0.9192

Max Act: 0.8119. Min Act: -0.0002

Data Index: 400892 (C4 (Web Text))

Max Activating Token Index: 597

Text #6

Max Range: 0.9192. Min Range: -0.9192

Max Act: 0.7479. Min Act: -0.0002

Data Index: 1282470 (C4 (Web Text))

Max Activating Token Index: 1007

Text #7

Max Range: 0.9192. Min Range: -0.9192

Max Act: 0.6925. Min Act: -0.0002

Data Index: 980669 (C4 (Web Text))

Max Activating Token Index: 630

Text #8

Max Range: 0.9192. Min Range: -0.9192

Max Act: 0.8180. Min Act: -0.0002

Data Index: 1252714 (C4 (Web Text))

Max Activating Token Index: 463

Text #9

Max Range: 0.9192. Min Range: -0.9192

Max Act: 0.7778. Min Act: -0.0002

Data Index: 50942 (C4 (Web Text))

Max Activating Token Index: 659

Text #10

Max Range: 0.9192. Min Range: -0.9192

Max Act: 0.7711. Min Act: -0.0002

Data Index: 1222149 (C4 (Web Text))

Max Activating Token Index: 337

Text #11

Max Range: 0.9192. Min Range: -0.9192

Max Act: 0.8386. Min Act: -0.0002

Data Index: 681862 (C4 (Web Text))

Max Activating Token Index: 880

Text #12

Max Range: 0.9192. Min Range: -0.9192

Max Act: 0.7245. Min Act: -0.0002

Data Index: 1331618 (C4 (Web Text))

Max Activating Token Index: 346

Text #13

Max Range: 0.9192. Min Range: -0.9192

Max Act: 0.8401. Min Act: -0.0002

Data Index: 167987 (C4 (Web Text))

Max Activating Token Index: 1012

Text #14

Max Range: 0.9192. Min Range: -0.9192

Max Act: 0.7557. Min Act: -0.0002

Data Index: 1041633 (C4 (Web Text))

Max Activating Token Index: 223

Text #15

Max Range: 0.9192. Min Range: -0.9192

Max Act: 0.7898. Min Act: -0.0002

Data Index: 162368 (C4 (Web Text))

Max Activating Token Index: 738

Text #16

Max Range: 0.9192. Min Range: -0.9192

Max Act: 0.8102. Min Act: -0.0002

Data Index: 1021025 (C4 (Web Text))

Max Activating Token Index: 906

Text #17

Max Range: 0.9192. Min Range: -0.9192

Max Act: 0.8074. Min Act: -0.0002

Data Index: 1010457 (C4 (Web Text))

Max Activating Token Index: 779

Text #18

Max Range: 0.9192. Min Range: -0.9192

Max Act: 0.8149. Min Act: -0.0002

Data Index: 367281 (C4 (Web Text))

Max Activating Token Index: 249

Text #19

Max Range: 0.9192. Min Range: -0.9192

Max Act: 0.6934. Min Act: -0.0002

Data Index: 1265372 (C4 (Web Text))

Max Activating Token Index: 111