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

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

Neuron 2207 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: 0.8670. Min Range: -0.8670

Max Act: 0.8670. Min Act: -0.0001

Data Index: 431853 (C4 (Web Text))

Max Activating Token Index: 897

Text #1

Max Range: 0.8670. Min Range: -0.8670

Max Act: 0.7391. Min Act: -0.0001

Data Index: 832053 (C4 (Web Text))

Max Activating Token Index: 325

Text #2

Max Range: 0.8670. Min Range: -0.8670

Max Act: 0.7053. Min Act: -0.0001

Data Index: 1335961 (C4 (Web Text))

Max Activating Token Index: 253

Text #3

Max Range: 0.8670. Min Range: -0.8670

Max Act: 0.6702. Min Act: -0.0001

Data Index: 835650 (C4 (Web Text))

Max Activating Token Index: 646

Text #4

Max Range: 0.8670. Min Range: -0.8670

Max Act: 0.6591. Min Act: -0.0001

Data Index: 427507 (C4 (Web Text))

Max Activating Token Index: 222

Text #5

Max Range: 0.8670. Min Range: -0.8670

Max Act: 0.6815. Min Act: -0.0001

Data Index: 663241 (C4 (Web Text))

Max Activating Token Index: 341

Text #6

Max Range: 0.8670. Min Range: -0.8670

Max Act: 0.6500. Min Act: -0.0001

Data Index: 924641 (C4 (Web Text))

Max Activating Token Index: 519

Text #7

Max Range: 0.8670. Min Range: -0.8670

Max Act: 0.6674. Min Act: -0.0000

Data Index: 1159223 (C4 (Web Text))

Max Activating Token Index: 439

Text #8

Max Range: 0.8670. Min Range: -0.8670

Max Act: 0.6037. Min Act: -0.0001

Data Index: 32826 (C4 (Web Text))

Max Activating Token Index: 745

Text #9

Max Range: 0.8670. Min Range: -0.8670

Max Act: 0.6429. Min Act: -0.0001

Data Index: 221258 (C4 (Web Text))

Max Activating Token Index: 334

Text #10

Max Range: 0.8670. Min Range: -0.8670

Max Act: 0.6419. Min Act: -0.0001

Data Index: 843019 (C4 (Web Text))

Max Activating Token Index: 142

Text #11

Max Range: 0.8670. Min Range: -0.8670

Max Act: 0.6220. Min Act: -0.0000

Data Index: 646067 (C4 (Web Text))

Max Activating Token Index: 927

Text #12

Max Range: 0.8670. Min Range: -0.8670

Max Act: 0.6210. Min Act: -0.0000

Data Index: 34769 (C4 (Web Text))

Max Activating Token Index: 672

Text #13

Max Range: 0.8670. Min Range: -0.8670

Max Act: 0.6379. Min Act: -0.0001

Data Index: 844675 (C4 (Web Text))

Max Activating Token Index: 543

Text #14

Max Range: 0.8670. Min Range: -0.8670

Max Act: 0.5966. Min Act: -0.0001

Data Index: 285861 (C4 (Web Text))

Max Activating Token Index: 408

Text #15

Max Range: 0.8670. Min Range: -0.8670

Max Act: 0.6069. Min Act: -0.0001

Data Index: 1069662 (C4 (Web Text))

Max Activating Token Index: 124

Text #16

Max Range: 0.8670. Min Range: -0.8670

Max Act: 0.6084. Min Act: -0.0001

Data Index: 636624 (C4 (Web Text))

Max Activating Token Index: 519

Text #17

Max Range: 0.8670. Min Range: -0.8670

Max Act: 0.6041. Min Act: -0.0000

Data Index: 1305961 (C4 (Web Text))

Max Activating Token Index: 817

Text #18

Max Range: 0.8670. Min Range: -0.8670

Max Act: 0.6205. Min Act: -0.0001

Data Index: 1353634 (C4 (Web Text))

Max Activating Token Index: 445

Text #19

Max Range: 0.8670. Min Range: -0.8670

Max Act: 0.6205. Min Act: -0.0000

Data Index: 1200148 (C4 (Web Text))

Max Activating Token Index: 234