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

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

Neuron 1572 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: 0.8789. Min Range: -0.8789

Max Act: 0.8543. Min Act: -0.0001

Data Index: 1096022 (C4 (Web Text))

Max Activating Token Index: 497

Text #1

Max Range: 0.8789. Min Range: -0.8789

Max Act: 0.8607. Min Act: -0.0000

Data Index: 167656 (C4 (Web Text))

Max Activating Token Index: 381

Text #2

Max Range: 0.8789. Min Range: -0.8789

Max Act: 0.8328. Min Act: -0.0001

Data Index: 410663 (C4 (Web Text))

Max Activating Token Index: 1008

Text #3

Max Range: 0.8789. Min Range: -0.8789

Max Act: 0.7858. Min Act: -0.0000

Data Index: 1266934 (C4 (Web Text))

Max Activating Token Index: 661

Text #4

Max Range: 0.8789. Min Range: -0.8789

Max Act: 0.8018. Min Act: -0.0000

Data Index: 537358 (C4 (Web Text))

Max Activating Token Index: 84

Text #5

Max Range: 0.8789. Min Range: -0.8789

Max Act: 0.7339. Min Act: -0.0000

Data Index: 539168 (C4 (Web Text))

Max Activating Token Index: 647

Text #6

Max Range: 0.8789. Min Range: -0.8789

Max Act: 0.7761. Min Act: -0.0000

Data Index: 1162943 (C4 (Web Text))

Max Activating Token Index: 192

Text #7

Max Range: 0.8789. Min Range: -0.8789

Max Act: 0.8226. Min Act: -0.0001

Data Index: 849158 (C4 (Web Text))

Max Activating Token Index: 540

Text #8

Max Range: 0.8789. Min Range: -0.8789

Max Act: 0.7860. Min Act: -0.0000

Data Index: 89209 (C4 (Web Text))

Max Activating Token Index: 527

Text #9

Max Range: 0.8789. Min Range: -0.8789

Max Act: 0.7593. Min Act: -0.0000

Data Index: 305675 (C4 (Web Text))

Max Activating Token Index: 195

Text #10

Max Range: 0.8789. Min Range: -0.8789

Max Act: 0.8789. Min Act: -0.0001

Data Index: 209109 (C4 (Web Text))

Max Activating Token Index: 773

Text #11

Max Range: 0.8789. Min Range: -0.8789

Max Act: 0.7756. Min Act: -0.0000

Data Index: 261477 (C4 (Web Text))

Max Activating Token Index: 917

Text #12

Max Range: 0.8789. Min Range: -0.8789

Max Act: 0.7874. Min Act: -0.0000

Data Index: 1105067 (C4 (Web Text))

Max Activating Token Index: 248

Text #13

Max Range: 0.8789. Min Range: -0.8789

Max Act: 0.7446. Min Act: -0.0001

Data Index: 1349051 (C4 (Web Text))

Max Activating Token Index: 479

Text #14

Max Range: 0.8789. Min Range: -0.8789

Max Act: 0.6744. Min Act: -0.0001

Data Index: 1139476 (C4 (Web Text))

Max Activating Token Index: 594

Text #15

Max Range: 0.8789. Min Range: -0.8789

Max Act: 0.7308. Min Act: -0.0000

Data Index: 218941 (C4 (Web Text))

Max Activating Token Index: 528

Text #16

Max Range: 0.8789. Min Range: -0.8789

Max Act: 0.7072. Min Act: -0.0000

Data Index: 392479 (C4 (Web Text))

Max Activating Token Index: 153

Text #17

Max Range: 0.8789. Min Range: -0.8789

Max Act: 0.7971. Min Act: -0.0000

Data Index: 400008 (C4 (Web Text))

Max Activating Token Index: 759

Text #18

Max Range: 0.8789. Min Range: -0.8789

Max Act: 0.7511. Min Act: -0.0000

Data Index: 1092304 (C4 (Web Text))

Max Activating Token Index: 665

Text #19

Max Range: 0.8789. Min Range: -0.8789

Max Act: 0.7448. Min Act: -0.0001

Data Index: 503200 (C4 (Web Text))

Max Activating Token Index: 916