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

Dataset: The Pile

Neuron 2853 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: 1.4750. Min Range: -1.4750

Max Act: 1.4750. Min Act: -0.0000

Data Index: 568639 (The Pile)

Max Activating Token Index: 662

Text #1

Max Range: 1.4750. Min Range: -1.4750

Max Act: 1.4675. Min Act: -0.0000

Data Index: 279350 (The Pile)

Max Activating Token Index: 130

Text #2

Max Range: 1.4750. Min Range: -1.4750

Max Act: 1.2324. Min Act: -0.0000

Data Index: 1397564 (The Pile)

Max Activating Token Index: 962

Text #3

Max Range: 1.4750. Min Range: -1.4750

Max Act: 1.2554. Min Act: -0.0000

Data Index: 1047102 (The Pile)

Max Activating Token Index: 455

Text #4

Max Range: 1.4750. Min Range: -1.4750

Max Act: 1.1306. Min Act: -0.0000

Data Index: 1966633 (The Pile)

Max Activating Token Index: 222

Text #5

Max Range: 1.4750. Min Range: -1.4750

Max Act: 1.1943. Min Act: -0.0000

Data Index: 600790 (The Pile)

Max Activating Token Index: 435

Text #6

Max Range: 1.4750. Min Range: -1.4750

Max Act: 1.1597. Min Act: -0.0000

Data Index: 1802004 (The Pile)

Max Activating Token Index: 161

Text #7

Max Range: 1.4750. Min Range: -1.4750

Max Act: 1.1466. Min Act: -0.0000

Data Index: 805608 (The Pile)

Max Activating Token Index: 427

Text #8

Max Range: 1.4750. Min Range: -1.4750

Max Act: 1.2045. Min Act: -0.0000

Data Index: 1520143 (The Pile)

Max Activating Token Index: 108

Text #9

Max Range: 1.4750. Min Range: -1.4750

Max Act: 1.0661. Min Act: -0.0000

Data Index: 1557666 (The Pile)

Max Activating Token Index: 180

Text #10

Max Range: 1.4750. Min Range: -1.4750

Max Act: 1.0949. Min Act: -0.0000

Data Index: 1584762 (The Pile)

Max Activating Token Index: 199

Text #11

Max Range: 1.4750. Min Range: -1.4750

Max Act: 1.0346. Min Act: -0.0000

Data Index: 1768067 (The Pile)

Max Activating Token Index: 873

Text #12

Max Range: 1.4750. Min Range: -1.4750

Max Act: 1.0771. Min Act: -0.0000

Data Index: 367797 (The Pile)

Max Activating Token Index: 186

Text #13

Max Range: 1.4750. Min Range: -1.4750

Max Act: 1.0993. Min Act: -0.0000

Data Index: 1454491 (The Pile)

Max Activating Token Index: 896

Text #14

Max Range: 1.4750. Min Range: -1.4750

Max Act: 1.0340. Min Act: -0.0000

Data Index: 392182 (The Pile)

Max Activating Token Index: 347

Text #15

Max Range: 1.4750. Min Range: -1.4750

Max Act: 1.0894. Min Act: -0.0000

Data Index: 52829 (The Pile)

Max Activating Token Index: 500

Text #16

Max Range: 1.4750. Min Range: -1.4750

Max Act: 1.0844. Min Act: -0.0000

Data Index: 1269076 (The Pile)

Max Activating Token Index: 329

Text #17

Max Range: 1.4750. Min Range: -1.4750

Max Act: 0.9707. Min Act: -0.0000

Data Index: 717645 (The Pile)

Max Activating Token Index: 999

Text #18

Max Range: 1.4750. Min Range: -1.4750

Max Act: 0.9990. Min Act: -0.0000

Data Index: 274638 (The Pile)

Max Activating Token Index: 808

Text #19

Max Range: 1.4750. Min Range: -1.4750

Max Act: 0.9277. Min Act: -0.0000

Data Index: 1382187 (The Pile)

Max Activating Token Index: 787