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

Dataset: The Pile

Neuron 1200 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: 0.6498. Min Range: -0.6498

Max Act: 0.6498. Min Act: -0.0000

Data Index: 249223 (The Pile)

Max Activating Token Index: 700

Text #1

Max Range: 0.6498. Min Range: -0.6498

Max Act: 0.6467. Min Act: -0.0000

Data Index: 1370300 (The Pile)

Max Activating Token Index: 169

Text #2

Max Range: 0.6498. Min Range: -0.6498

Max Act: 0.6036. Min Act: -0.0000

Data Index: 1107092 (The Pile)

Max Activating Token Index: 117

Text #3

Max Range: 0.6498. Min Range: -0.6498

Max Act: 0.5801. Min Act: -0.0000

Data Index: 1482207 (The Pile)

Max Activating Token Index: 352

Text #4

Max Range: 0.6498. Min Range: -0.6498

Max Act: 0.5944. Min Act: -0.0000

Data Index: 491133 (The Pile)

Max Activating Token Index: 721

Text #5

Max Range: 0.6498. Min Range: -0.6498

Max Act: 0.5902. Min Act: -0.0000

Data Index: 859312 (The Pile)

Max Activating Token Index: 194

Text #6

Max Range: 0.6498. Min Range: -0.6498

Max Act: 0.5556. Min Act: -0.0000

Data Index: 1056080 (The Pile)

Max Activating Token Index: 49

Text #7

Max Range: 0.6498. Min Range: -0.6498

Max Act: 0.5361. Min Act: -0.0000

Data Index: 1152693 (The Pile)

Max Activating Token Index: 1004

Text #8

Max Range: 0.6498. Min Range: -0.6498

Max Act: 0.5464. Min Act: -0.0000

Data Index: 1514173 (The Pile)

Max Activating Token Index: 320

Text #9

Max Range: 0.6498. Min Range: -0.6498

Max Act: 0.5407. Min Act: -0.0000

Data Index: 473711 (The Pile)

Max Activating Token Index: 80

Text #10

Max Range: 0.6498. Min Range: -0.6498

Max Act: 0.5188. Min Act: -0.0000

Data Index: 222226 (The Pile)

Max Activating Token Index: 68

Text #11

Max Range: 0.6498. Min Range: -0.6498

Max Act: 0.5162. Min Act: -0.0000

Data Index: 825662 (The Pile)

Max Activating Token Index: 227

Text #12

Max Range: 0.6498. Min Range: -0.6498

Max Act: 0.4790. Min Act: -0.0000

Data Index: 643403 (The Pile)

Max Activating Token Index: 58

Text #13

Max Range: 0.6498. Min Range: -0.6498

Max Act: 0.5130. Min Act: -0.0000

Data Index: 1752398 (The Pile)

Max Activating Token Index: 123

Text #14

Max Range: 0.6498. Min Range: -0.6498

Max Act: 0.4963. Min Act: -0.0000

Data Index: 1303975 (The Pile)

Max Activating Token Index: 858

Text #15

Max Range: 0.6498. Min Range: -0.6498

Max Act: 0.4943. Min Act: -0.0000

Data Index: 1278507 (The Pile)

Max Activating Token Index: 1010

Text #16

Max Range: 0.6498. Min Range: -0.6498

Max Act: 0.4954. Min Act: -0.0000

Data Index: 833382 (The Pile)

Max Activating Token Index: 130

Text #17

Max Range: 0.6498. Min Range: -0.6498

Max Act: 0.4926. Min Act: -0.0000

Data Index: 1022162 (The Pile)

Max Activating Token Index: 1006

Text #18

Max Range: 0.6498. Min Range: -0.6498

Max Act: 0.4907. Min Act: -0.0000

Data Index: 123098 (The Pile)

Max Activating Token Index: 304

Text #19

Max Range: 0.6498. Min Range: -0.6498

Max Act: 0.4887. Min Act: -0.0000

Data Index: 913308 (The Pile)

Max Activating Token Index: 565