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

Dataset: The Pile

Neuron 4602 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: 1.1897. Min Range: -1.1897

Max Act: 1.1897. Min Act: -0.0000

Data Index: 409128 (The Pile)

Max Activating Token Index: 221

Text #1

Max Range: 1.1897. Min Range: -1.1897

Max Act: 1.0273. Min Act: -0.0000

Data Index: 1549918 (The Pile)

Max Activating Token Index: 88

Text #2

Max Range: 1.1897. Min Range: -1.1897

Max Act: 0.9972. Min Act: -0.0000

Data Index: 904040 (The Pile)

Max Activating Token Index: 297

Text #3

Max Range: 1.1897. Min Range: -1.1897

Max Act: 1.0039. Min Act: -0.0000

Data Index: 1342993 (The Pile)

Max Activating Token Index: 165

Text #4

Max Range: 1.1897. Min Range: -1.1897

Max Act: 0.9130. Min Act: -0.0000

Data Index: 445927 (The Pile)

Max Activating Token Index: 499

Text #5

Max Range: 1.1897. Min Range: -1.1897

Max Act: 0.9004. Min Act: -0.0000

Data Index: 1283896 (The Pile)

Max Activating Token Index: 518

Text #6

Max Range: 1.1897. Min Range: -1.1897

Max Act: 0.9830. Min Act: -0.0000

Data Index: 1310619 (The Pile)

Max Activating Token Index: 827

Text #7

Max Range: 1.1897. Min Range: -1.1897

Max Act: 0.8965. Min Act: -0.0000

Data Index: 486925 (The Pile)

Max Activating Token Index: 153

Text #8

Max Range: 1.1897. Min Range: -1.1897

Max Act: 0.8917. Min Act: -0.0000

Data Index: 1715475 (The Pile)

Max Activating Token Index: 206

Text #9

Max Range: 1.1897. Min Range: -1.1897

Max Act: 0.8332. Min Act: -0.0000

Data Index: 1814623 (The Pile)

Max Activating Token Index: 175

Text #10

Max Range: 1.1897. Min Range: -1.1897

Max Act: 0.8285. Min Act: -0.0000

Data Index: 1908351 (The Pile)

Max Activating Token Index: 203

Text #11

Max Range: 1.1897. Min Range: -1.1897

Max Act: 0.9925. Min Act: -0.0000

Data Index: 297040 (The Pile)

Max Activating Token Index: 118

Text #12

Max Range: 1.1897. Min Range: -1.1897

Max Act: 0.8437. Min Act: -0.0000

Data Index: 284064 (The Pile)

Max Activating Token Index: 552

Text #13

Max Range: 1.1897. Min Range: -1.1897

Max Act: 0.8363. Min Act: -0.0000

Data Index: 418143 (The Pile)

Max Activating Token Index: 777

Text #14

Max Range: 1.1897. Min Range: -1.1897

Max Act: 0.8248. Min Act: -0.0000

Data Index: 3288 (The Pile)

Max Activating Token Index: 148

Text #15

Max Range: 1.1897. Min Range: -1.1897

Max Act: 0.8348. Min Act: -0.0000

Data Index: 1655703 (The Pile)

Max Activating Token Index: 822

Text #16

Max Range: 1.1897. Min Range: -1.1897

Max Act: 0.8432. Min Act: -0.0000

Data Index: 424297 (The Pile)

Max Activating Token Index: 831

Text #17

Max Range: 1.1897. Min Range: -1.1897

Max Act: 0.8722. Min Act: -0.0000

Data Index: 1811342 (The Pile)

Max Activating Token Index: 436

Text #18

Max Range: 1.1897. Min Range: -1.1897

Max Act: 0.8301. Min Act: -0.0000

Data Index: 190367 (The Pile)

Max Activating Token Index: 70

Text #19

Max Range: 1.1897. Min Range: -1.1897

Max Act: 0.7984. Min Act: -0.0000

Data Index: 1837456 (The Pile)

Max Activating Token Index: 82