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

Dataset: The Pile

Neuron 2221 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: 1.0161. Min Range: -1.0161

Max Act: 1.0161. Min Act: 0.0000

Data Index: 410849 (The Pile)

Max Activating Token Index: 929

Text #1

Max Range: 1.0161. Min Range: -1.0161

Max Act: 0.7757. Min Act: 0.0000

Data Index: 97821 (The Pile)

Max Activating Token Index: 951

Text #2

Max Range: 1.0161. Min Range: -1.0161

Max Act: 0.6873. Min Act: -0.0000

Data Index: 626152 (The Pile)

Max Activating Token Index: 919

Text #3

Max Range: 1.0161. Min Range: -1.0161

Max Act: 0.6777. Min Act: -0.0000

Data Index: 754072 (The Pile)

Max Activating Token Index: 220

Text #4

Max Range: 1.0161. Min Range: -1.0161

Max Act: 0.6591. Min Act: 0.0000

Data Index: 821482 (The Pile)

Max Activating Token Index: 438

Text #5

Max Range: 1.0161. Min Range: -1.0161

Max Act: 0.6571. Min Act: -0.0000

Data Index: 1844177 (The Pile)

Max Activating Token Index: 109

Text #6

Max Range: 1.0161. Min Range: -1.0161

Max Act: 0.5896. Min Act: -0.0000

Data Index: 1733293 (The Pile)

Max Activating Token Index: 948

Text #7

Max Range: 1.0161. Min Range: -1.0161

Max Act: 0.4781. Min Act: -0.0000

Data Index: 484523 (The Pile)

Max Activating Token Index: 511

Text #8

Max Range: 1.0161. Min Range: -1.0161

Max Act: 0.5468. Min Act: -0.0000

Data Index: 764415 (The Pile)

Max Activating Token Index: 36

Text #9

Max Range: 1.0161. Min Range: -1.0161

Max Act: 0.5684. Min Act: -0.0000

Data Index: 1971121 (The Pile)

Max Activating Token Index: 851

Text #10

Max Range: 1.0161. Min Range: -1.0161

Max Act: 0.4961. Min Act: -0.0000

Data Index: 1275506 (The Pile)

Max Activating Token Index: 431

Text #11

Max Range: 1.0161. Min Range: -1.0161

Max Act: 0.6194. Min Act: -0.0000

Data Index: 420039 (The Pile)

Max Activating Token Index: 147

Text #12

Max Range: 1.0161. Min Range: -1.0161

Max Act: 0.5557. Min Act: 0.0000

Data Index: 1929953 (The Pile)

Max Activating Token Index: 24

Text #13

Max Range: 1.0161. Min Range: -1.0161

Max Act: 0.4876. Min Act: 0.0000

Data Index: 1679359 (The Pile)

Max Activating Token Index: 778

Text #14

Max Range: 1.0161. Min Range: -1.0161

Max Act: 0.5166. Min Act: 0.0000

Data Index: 1434536 (The Pile)

Max Activating Token Index: 753

Text #15

Max Range: 1.0161. Min Range: -1.0161

Max Act: 0.4953. Min Act: -0.0000

Data Index: 688572 (The Pile)

Max Activating Token Index: 929

Text #16

Max Range: 1.0161. Min Range: -1.0161

Max Act: 0.4809. Min Act: -0.0000

Data Index: 1609162 (The Pile)

Max Activating Token Index: 811

Text #17

Max Range: 1.0161. Min Range: -1.0161

Max Act: 0.4502. Min Act: -0.0000

Data Index: 1133529 (The Pile)

Max Activating Token Index: 348

Text #18

Max Range: 1.0161. Min Range: -1.0161

Max Act: 0.4537. Min Act: 0.0000

Data Index: 1686577 (The Pile)

Max Activating Token Index: 545

Text #19

Max Range: 1.0161. Min Range: -1.0161

Max Act: 0.4629. Min Act: -0.0000

Data Index: 1905812 (The Pile)

Max Activating Token Index: 294