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

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

Neuron 587 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7885. Min Range: -1.7885

Max Act: 1.7885. Min Act: -0.0000

Data Index: 344109 (C4 (Web Text))

Max Activating Token Index: 306

Text #1

Max Range: 1.7885. Min Range: -1.7885

Max Act: 1.3397. Min Act: -0.0000

Data Index: 198837 (C4 (Web Text))

Max Activating Token Index: 48

Text #2

Max Range: 1.7885. Min Range: -1.7885

Max Act: 1.3372. Min Act: -0.0000

Data Index: 401517 (C4 (Web Text))

Max Activating Token Index: 781

Text #3

Max Range: 1.7885. Min Range: -1.7885

Max Act: 1.1478. Min Act: -0.0000

Data Index: 350820 (C4 (Web Text))

Max Activating Token Index: 917

Text #4

Max Range: 1.7885. Min Range: -1.7885

Max Act: 1.1139. Min Act: -0.0000

Data Index: 1285590 (C4 (Web Text))

Max Activating Token Index: 30

Text #5

Max Range: 1.7885. Min Range: -1.7885

Max Act: 1.1408. Min Act: -0.0000

Data Index: 814119 (C4 (Web Text))

Max Activating Token Index: 116

Text #6

Max Range: 1.7885. Min Range: -1.7885

Max Act: 1.0627. Min Act: -0.0000

Data Index: 553252 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 1.7885. Min Range: -1.7885

Max Act: 1.0248. Min Act: -0.0000

Data Index: 1143503 (C4 (Web Text))

Max Activating Token Index: 273

Text #8

Max Range: 1.7885. Min Range: -1.7885

Max Act: 1.0552. Min Act: -0.0000

Data Index: 772671 (C4 (Web Text))

Max Activating Token Index: 624

Text #9

Max Range: 1.7885. Min Range: -1.7885

Max Act: 1.0011. Min Act: -0.0000

Data Index: 181394 (C4 (Web Text))

Max Activating Token Index: 589

Text #10

Max Range: 1.7885. Min Range: -1.7885

Max Act: 1.0400. Min Act: -0.0000

Data Index: 1223331 (C4 (Web Text))

Max Activating Token Index: 411

Text #11

Max Range: 1.7885. Min Range: -1.7885

Max Act: 1.0725. Min Act: -0.0000

Data Index: 618599 (C4 (Web Text))

Max Activating Token Index: 35

Text #12

Max Range: 1.7885. Min Range: -1.7885

Max Act: 0.9349. Min Act: -0.0000

Data Index: 448954 (C4 (Web Text))

Max Activating Token Index: 168

Text #13

Max Range: 1.7885. Min Range: -1.7885

Max Act: 0.9293. Min Act: -0.0000

Data Index: 713104 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 1.7885. Min Range: -1.7885

Max Act: 1.0078. Min Act: -0.0000

Data Index: 526414 (C4 (Web Text))

Max Activating Token Index: 967

Text #15

Max Range: 1.7885. Min Range: -1.7885

Max Act: 0.9381. Min Act: -0.0000

Data Index: 729492 (C4 (Web Text))

Max Activating Token Index: 218

Text #16

Max Range: 1.7885. Min Range: -1.7885

Max Act: 0.9608. Min Act: -0.0000

Data Index: 208470 (C4 (Web Text))

Max Activating Token Index: 296

Text #17

Max Range: 1.7885. Min Range: -1.7885

Max Act: 0.9542. Min Act: -0.0000

Data Index: 493020 (C4 (Web Text))

Max Activating Token Index: 65

Text #18

Max Range: 1.7885. Min Range: -1.7885

Max Act: 0.9148. Min Act: -0.0000

Data Index: 1162229 (C4 (Web Text))

Max Activating Token Index: 806

Text #19

Max Range: 1.7885. Min Range: -1.7885

Max Act: 0.9092. Min Act: -0.0000

Data Index: 195873 (C4 (Web Text))

Max Activating Token Index: 1018