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

Dataset: The Pile

Neuron 1089 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0580. Min Range: -1.0580

Max Act: 1.0500. Min Act: -0.0000

Data Index: 1925348 (The Pile)

Max Activating Token Index: 230

Text #1

Max Range: 1.0580. Min Range: -1.0580

Max Act: 1.0221. Min Act: -0.0000

Data Index: 700328 (The Pile)

Max Activating Token Index: 831

Text #2

Max Range: 1.0580. Min Range: -1.0580

Max Act: 0.8863. Min Act: -0.0000

Data Index: 544065 (The Pile)

Max Activating Token Index: 204

Text #3

Max Range: 1.0580. Min Range: -1.0580

Max Act: 0.9405. Min Act: -0.0000

Data Index: 1802783 (The Pile)

Max Activating Token Index: 817

Text #4

Max Range: 1.0580. Min Range: -1.0580

Max Act: 1.0580. Min Act: -0.0000

Data Index: 737719 (The Pile)

Max Activating Token Index: 16

Text #5

Max Range: 1.0580. Min Range: -1.0580

Max Act: 0.9772. Min Act: -0.0000

Data Index: 914937 (The Pile)

Max Activating Token Index: 866

Text #6

Max Range: 1.0580. Min Range: -1.0580

Max Act: 0.9822. Min Act: -0.0000

Data Index: 1557820 (The Pile)

Max Activating Token Index: 663

Text #7

Max Range: 1.0580. Min Range: -1.0580

Max Act: 0.9625. Min Act: -0.0000

Data Index: 22699 (The Pile)

Max Activating Token Index: 890

Text #8

Max Range: 1.0580. Min Range: -1.0580

Max Act: 0.9756. Min Act: -0.0000

Data Index: 808320 (The Pile)

Max Activating Token Index: 209

Text #9

Max Range: 1.0580. Min Range: -1.0580

Max Act: 0.9377. Min Act: -0.0000

Data Index: 728572 (The Pile)

Max Activating Token Index: 421

Text #10

Max Range: 1.0580. Min Range: -1.0580

Max Act: 0.8528. Min Act: -0.0000

Data Index: 1370413 (The Pile)

Max Activating Token Index: 1002

Text #11

Max Range: 1.0580. Min Range: -1.0580

Max Act: 0.9241. Min Act: -0.0000

Data Index: 1124702 (The Pile)

Max Activating Token Index: 584

Text #12

Max Range: 1.0580. Min Range: -1.0580

Max Act: 0.9491. Min Act: -0.0000

Data Index: 46580 (The Pile)

Max Activating Token Index: 520

Text #13

Max Range: 1.0580. Min Range: -1.0580

Max Act: 0.9160. Min Act: -0.0000

Data Index: 1005299 (The Pile)

Max Activating Token Index: 390

Text #14

Max Range: 1.0580. Min Range: -1.0580

Max Act: 0.8703. Min Act: -0.0000

Data Index: 185376 (The Pile)

Max Activating Token Index: 61

Text #15

Max Range: 1.0580. Min Range: -1.0580

Max Act: 0.8844. Min Act: -0.0000

Data Index: 343702 (The Pile)

Max Activating Token Index: 710

Text #16

Max Range: 1.0580. Min Range: -1.0580

Max Act: 0.8646. Min Act: -0.0000

Data Index: 121262 (The Pile)

Max Activating Token Index: 47

Text #17

Max Range: 1.0580. Min Range: -1.0580

Max Act: 0.8916. Min Act: -0.0000

Data Index: 560955 (The Pile)

Max Activating Token Index: 689

Text #18

Max Range: 1.0580. Min Range: -1.0580

Max Act: 0.8621. Min Act: -0.0000

Data Index: 1871236 (The Pile)

Max Activating Token Index: 564

Text #19

Max Range: 1.0580. Min Range: -1.0580

Max Act: 0.7936. Min Act: -0.0000

Data Index: 895853 (The Pile)

Max Activating Token Index: 845