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

Dataset: The Pile

Neuron 3378 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2347. Min Range: -1.2347

Max Act: 1.2344. Min Act: -0.0000

Data Index: 200714 (The Pile)

Max Activating Token Index: 399

Text #1

Max Range: 1.2347. Min Range: -1.2347

Max Act: 1.2347. Min Act: -0.0000

Data Index: 59831 (The Pile)

Max Activating Token Index: 13

Text #2

Max Range: 1.2347. Min Range: -1.2347

Max Act: 1.1196. Min Act: -0.0000

Data Index: 1843268 (The Pile)

Max Activating Token Index: 252

Text #3

Max Range: 1.2347. Min Range: -1.2347

Max Act: 0.9639. Min Act: -0.0000

Data Index: 651543 (The Pile)

Max Activating Token Index: 82

Text #4

Max Range: 1.2347. Min Range: -1.2347

Max Act: 0.9853. Min Act: -0.0000

Data Index: 15812 (The Pile)

Max Activating Token Index: 541

Text #5

Max Range: 1.2347. Min Range: -1.2347

Max Act: 0.9509. Min Act: -0.0000

Data Index: 1820886 (The Pile)

Max Activating Token Index: 657

Text #6

Max Range: 1.2347. Min Range: -1.2347

Max Act: 0.9330. Min Act: -0.0000

Data Index: 309931 (The Pile)

Max Activating Token Index: 233

Text #7

Max Range: 1.2347. Min Range: -1.2347

Max Act: 0.8868. Min Act: -0.0000

Data Index: 495238 (The Pile)

Max Activating Token Index: 504

Text #8

Max Range: 1.2347. Min Range: -1.2347

Max Act: 0.9469. Min Act: -0.0000

Data Index: 1088006 (The Pile)

Max Activating Token Index: 214

Text #9

Max Range: 1.2347. Min Range: -1.2347

Max Act: 0.8899. Min Act: -0.0000

Data Index: 1494640 (The Pile)

Max Activating Token Index: 683

Text #10

Max Range: 1.2347. Min Range: -1.2347

Max Act: 0.8606. Min Act: -0.0000

Data Index: 1021664 (The Pile)

Max Activating Token Index: 855

Text #11

Max Range: 1.2347. Min Range: -1.2347

Max Act: 0.8567. Min Act: -0.0000

Data Index: 1671807 (The Pile)

Max Activating Token Index: 61

Text #12

Max Range: 1.2347. Min Range: -1.2347

Max Act: 0.7721. Min Act: -0.0000

Data Index: 1675707 (The Pile)

Max Activating Token Index: 956

Text #13

Max Range: 1.2347. Min Range: -1.2347

Max Act: 0.7700. Min Act: -0.0000

Data Index: 942528 (The Pile)

Max Activating Token Index: 31

Text #14

Max Range: 1.2347. Min Range: -1.2347

Max Act: 0.8423. Min Act: -0.0000

Data Index: 759722 (The Pile)

Max Activating Token Index: 587

Text #15

Max Range: 1.2347. Min Range: -1.2347

Max Act: 0.7786. Min Act: -0.0000

Data Index: 1694732 (The Pile)

Max Activating Token Index: 33

Text #16

Max Range: 1.2347. Min Range: -1.2347

Max Act: 0.7718. Min Act: -0.0000

Data Index: 804151 (The Pile)

Max Activating Token Index: 152

Text #17

Max Range: 1.2347. Min Range: -1.2347

Max Act: 0.7887. Min Act: -0.0000

Data Index: 1495329 (The Pile)

Max Activating Token Index: 261

Text #18

Max Range: 1.2347. Min Range: -1.2347

Max Act: 0.7898. Min Act: -0.0000

Data Index: 1265115 (The Pile)

Max Activating Token Index: 373

Text #19

Max Range: 1.2347. Min Range: -1.2347

Max Act: 0.7620. Min Act: -0.0000

Data Index: 544279 (The Pile)

Max Activating Token Index: 87