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

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

Neuron 2745 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9515. Min Range: -0.9515

Max Act: 0.9515. Min Act: -0.0000

Data Index: 197071 (C4 (Web Text))

Max Activating Token Index: 227

Text #1

Max Range: 0.9515. Min Range: -0.9515

Max Act: 0.8858. Min Act: -0.0000

Data Index: 442801 (C4 (Web Text))

Max Activating Token Index: 439

Text #2

Max Range: 0.9515. Min Range: -0.9515

Max Act: 0.7873. Min Act: -0.0000

Data Index: 712345 (C4 (Web Text))

Max Activating Token Index: 782

Text #3

Max Range: 0.9515. Min Range: -0.9515

Max Act: 0.7279. Min Act: -0.0000

Data Index: 983227 (C4 (Web Text))

Max Activating Token Index: 891

Text #4

Max Range: 0.9515. Min Range: -0.9515

Max Act: 0.7646. Min Act: -0.0000

Data Index: 1253788 (C4 (Web Text))

Max Activating Token Index: 489

Text #5

Max Range: 0.9515. Min Range: -0.9515

Max Act: 0.7476. Min Act: -0.0000

Data Index: 513433 (C4 (Web Text))

Max Activating Token Index: 145

Text #6

Max Range: 0.9515. Min Range: -0.9515

Max Act: 0.7425. Min Act: -0.0000

Data Index: 835367 (C4 (Web Text))

Max Activating Token Index: 938

Text #7

Max Range: 0.9515. Min Range: -0.9515

Max Act: 0.7199. Min Act: -0.0000

Data Index: 1298686 (C4 (Web Text))

Max Activating Token Index: 170

Text #8

Max Range: 0.9515. Min Range: -0.9515

Max Act: 0.6857. Min Act: -0.0000

Data Index: 852900 (C4 (Web Text))

Max Activating Token Index: 105

Text #9

Max Range: 0.9515. Min Range: -0.9515

Max Act: 0.6648. Min Act: -0.0000

Data Index: 195187 (C4 (Web Text))

Max Activating Token Index: 925

Text #10

Max Range: 0.9515. Min Range: -0.9515

Max Act: 0.7287. Min Act: 0.0000

Data Index: 421620 (C4 (Web Text))

Max Activating Token Index: 861

Text #11

Max Range: 0.9515. Min Range: -0.9515

Max Act: 0.7212. Min Act: -0.0000

Data Index: 110459 (C4 (Web Text))

Max Activating Token Index: 292

Text #12

Max Range: 0.9515. Min Range: -0.9515

Max Act: 0.6772. Min Act: -0.0000

Data Index: 697903 (C4 (Web Text))

Max Activating Token Index: 705

Text #13

Max Range: 0.9515. Min Range: -0.9515

Max Act: 0.6965. Min Act: -0.0000

Data Index: 172564 (C4 (Web Text))

Max Activating Token Index: 537

Text #14

Max Range: 0.9515. Min Range: -0.9515

Max Act: 0.6933. Min Act: -0.0000

Data Index: 555461 (C4 (Web Text))

Max Activating Token Index: 576

Text #15

Max Range: 0.9515. Min Range: -0.9515

Max Act: 0.6842. Min Act: -0.0000

Data Index: 61647 (C4 (Web Text))

Max Activating Token Index: 60

Text #16

Max Range: 0.9515. Min Range: -0.9515

Max Act: 0.6797. Min Act: -0.0000

Data Index: 1289337 (C4 (Web Text))

Max Activating Token Index: 288

Text #17

Max Range: 0.9515. Min Range: -0.9515

Max Act: 0.6645. Min Act: -0.0000

Data Index: 826150 (C4 (Web Text))

Max Activating Token Index: 179

Text #18

Max Range: 0.9515. Min Range: -0.9515

Max Act: 0.7286. Min Act: -0.0000

Data Index: 1017852 (C4 (Web Text))

Max Activating Token Index: 249

Text #19

Max Range: 0.9515. Min Range: -0.9515

Max Act: 0.6798. Min Act: -0.0000

Data Index: 829136 (C4 (Web Text))

Max Activating Token Index: 993