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

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

Neuron 1189 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: 1.0316. Min Range: -1.0316

Max Act: 0.9741. Min Act: -0.0000

Data Index: 841509 (C4 (Web Text))

Max Activating Token Index: 755

Text #1

Max Range: 1.0316. Min Range: -1.0316

Max Act: 1.0316. Min Act: -0.0000

Data Index: 1298558 (C4 (Web Text))

Max Activating Token Index: 40

Text #2

Max Range: 1.0316. Min Range: -1.0316

Max Act: 0.9597. Min Act: -0.0000

Data Index: 168323 (C4 (Web Text))

Max Activating Token Index: 515

Text #3

Max Range: 1.0316. Min Range: -1.0316

Max Act: 0.8778. Min Act: -0.0000

Data Index: 339108 (C4 (Web Text))

Max Activating Token Index: 291

Text #4

Max Range: 1.0316. Min Range: -1.0316

Max Act: 0.9782. Min Act: -0.0000

Data Index: 97211 (C4 (Web Text))

Max Activating Token Index: 730

Text #5

Max Range: 1.0316. Min Range: -1.0316

Max Act: 0.8167. Min Act: -0.0000

Data Index: 184845 (C4 (Web Text))

Max Activating Token Index: 955

Text #6

Max Range: 1.0316. Min Range: -1.0316

Max Act: 0.8487. Min Act: -0.0000

Data Index: 344378 (C4 (Web Text))

Max Activating Token Index: 410

Text #7

Max Range: 1.0316. Min Range: -1.0316

Max Act: 0.8102. Min Act: -0.0000

Data Index: 1225649 (C4 (Web Text))

Max Activating Token Index: 264

Text #8

Max Range: 1.0316. Min Range: -1.0316

Max Act: 0.8212. Min Act: -0.0000

Data Index: 223959 (C4 (Web Text))

Max Activating Token Index: 240

Text #9

Max Range: 1.0316. Min Range: -1.0316

Max Act: 0.8246. Min Act: -0.0000

Data Index: 93600 (C4 (Web Text))

Max Activating Token Index: 247

Text #10

Max Range: 1.0316. Min Range: -1.0316

Max Act: 0.7918. Min Act: -0.0000

Data Index: 1115136 (C4 (Web Text))

Max Activating Token Index: 512

Text #11

Max Range: 1.0316. Min Range: -1.0316

Max Act: 0.7182. Min Act: -0.0000

Data Index: 473435 (C4 (Web Text))

Max Activating Token Index: 917

Text #12

Max Range: 1.0316. Min Range: -1.0316

Max Act: 0.7787. Min Act: -0.0000

Data Index: 673597 (C4 (Web Text))

Max Activating Token Index: 940

Text #13

Max Range: 1.0316. Min Range: -1.0316

Max Act: 0.7506. Min Act: -0.0000

Data Index: 1186608 (C4 (Web Text))

Max Activating Token Index: 85

Text #14

Max Range: 1.0316. Min Range: -1.0316

Max Act: 0.7306. Min Act: -0.0000

Data Index: 686178 (C4 (Web Text))

Max Activating Token Index: 796

Text #15

Max Range: 1.0316. Min Range: -1.0316

Max Act: 0.7838. Min Act: -0.0000

Data Index: 432767 (C4 (Web Text))

Max Activating Token Index: 332

Text #16

Max Range: 1.0316. Min Range: -1.0316

Max Act: 0.6502. Min Act: -0.0000

Data Index: 524328 (C4 (Web Text))

Max Activating Token Index: 845

Text #17

Max Range: 1.0316. Min Range: -1.0316

Max Act: 0.7096. Min Act: -0.0000

Data Index: 299098 (C4 (Web Text))

Max Activating Token Index: 764

Text #18

Max Range: 1.0316. Min Range: -1.0316

Max Act: 0.7429. Min Act: -0.0000

Data Index: 294822 (C4 (Web Text))

Max Activating Token Index: 761

Text #19

Max Range: 1.0316. Min Range: -1.0316

Max Act: 0.6516. Min Act: -0.0000

Data Index: 124282 (C4 (Web Text))

Max Activating Token Index: 644