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

Dataset: The Pile

Neuron 3559 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.3614. Min Range: -0.3614

Max Act: 0.3614. Min Act: -0.0000

Data Index: 552114 (The Pile)

Max Activating Token Index: 317

Text #1

Max Range: 0.3614. Min Range: -0.3614

Max Act: 0.3358. Min Act: -0.0000

Data Index: 1773721 (The Pile)

Max Activating Token Index: 498

Text #2

Max Range: 0.3614. Min Range: -0.3614

Max Act: 0.3168. Min Act: -0.0000

Data Index: 1329164 (The Pile)

Max Activating Token Index: 421

Text #3

Max Range: 0.3614. Min Range: -0.3614

Max Act: 0.3355. Min Act: -0.0000

Data Index: 694276 (The Pile)

Max Activating Token Index: 27

Text #4

Max Range: 0.3614. Min Range: -0.3614

Max Act: 0.3161. Min Act: 0.0000

Data Index: 1905958 (The Pile)

Max Activating Token Index: 1003

Text #5

Max Range: 0.3614. Min Range: -0.3614

Max Act: 0.3056. Min Act: -0.0000

Data Index: 1225897 (The Pile)

Max Activating Token Index: 380

Text #6

Max Range: 0.3614. Min Range: -0.3614

Max Act: 0.3004. Min Act: -0.0000

Data Index: 229929 (The Pile)

Max Activating Token Index: 948

Text #7

Max Range: 0.3614. Min Range: -0.3614

Max Act: 0.3044. Min Act: -0.0000

Data Index: 656147 (The Pile)

Max Activating Token Index: 221

Text #8

Max Range: 0.3614. Min Range: -0.3614

Max Act: 0.2817. Min Act: 0.0000

Data Index: 1375561 (The Pile)

Max Activating Token Index: 132

Text #9

Max Range: 0.3614. Min Range: -0.3614

Max Act: 0.2917. Min Act: -0.0000

Data Index: 1230511 (The Pile)

Max Activating Token Index: 311

Text #10

Max Range: 0.3614. Min Range: -0.3614

Max Act: 0.2878. Min Act: -0.0000

Data Index: 808967 (The Pile)

Max Activating Token Index: 191

Text #11

Max Range: 0.3614. Min Range: -0.3614

Max Act: 0.2698. Min Act: 0.0000

Data Index: 203814 (The Pile)

Max Activating Token Index: 481

Text #12

Max Range: 0.3614. Min Range: -0.3614

Max Act: 0.2559. Min Act: -0.0000

Data Index: 116762 (The Pile)

Max Activating Token Index: 549

Text #13

Max Range: 0.3614. Min Range: -0.3614

Max Act: 0.2745. Min Act: -0.0000

Data Index: 1010125 (The Pile)

Max Activating Token Index: 852

Text #14

Max Range: 0.3614. Min Range: -0.3614

Max Act: 0.2758. Min Act: -0.0000

Data Index: 924108 (The Pile)

Max Activating Token Index: 516

Text #15

Max Range: 0.3614. Min Range: -0.3614

Max Act: 0.2466. Min Act: -0.0000

Data Index: 1673965 (The Pile)

Max Activating Token Index: 736

Text #16

Max Range: 0.3614. Min Range: -0.3614

Max Act: 0.2702. Min Act: -0.0000

Data Index: 920428 (The Pile)

Max Activating Token Index: 672

Text #17

Max Range: 0.3614. Min Range: -0.3614

Max Act: 0.2354. Min Act: 0.0000

Data Index: 458306 (The Pile)

Max Activating Token Index: 33

Text #18

Max Range: 0.3614. Min Range: -0.3614

Max Act: 0.2663. Min Act: -0.0000

Data Index: 1796928 (The Pile)

Max Activating Token Index: 200

Text #19

Max Range: 0.3614. Min Range: -0.3614

Max Act: 0.2490. Min Act: -0.0000

Data Index: 1857569 (The Pile)

Max Activating Token Index: 816