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

Dataset: The Pile

Neuron 2580 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8113. Min Range: -0.8113

Max Act: 0.8113. Min Act: -0.0000

Data Index: 1963236 (The Pile)

Max Activating Token Index: 293

Text #1

Max Range: 0.8113. Min Range: -0.8113

Max Act: 0.7914. Min Act: -0.0000

Data Index: 767328 (The Pile)

Max Activating Token Index: 193

Text #2

Max Range: 0.8113. Min Range: -0.8113

Max Act: 0.7111. Min Act: -0.0000

Data Index: 1838186 (The Pile)

Max Activating Token Index: 911

Text #3

Max Range: 0.8113. Min Range: -0.8113

Max Act: 0.6643. Min Act: -0.0000

Data Index: 1889353 (The Pile)

Max Activating Token Index: 284

Text #4

Max Range: 0.8113. Min Range: -0.8113

Max Act: 0.6997. Min Act: -0.0000

Data Index: 1639300 (The Pile)

Max Activating Token Index: 489

Text #5

Max Range: 0.8113. Min Range: -0.8113

Max Act: 0.6499. Min Act: -0.0000

Data Index: 1235761 (The Pile)

Max Activating Token Index: 193

Text #6

Max Range: 0.8113. Min Range: -0.8113

Max Act: 0.6243. Min Act: -0.0000

Data Index: 1659826 (The Pile)

Max Activating Token Index: 752

Text #7

Max Range: 0.8113. Min Range: -0.8113

Max Act: 0.6313. Min Act: -0.0000

Data Index: 1872833 (The Pile)

Max Activating Token Index: 404

Text #8

Max Range: 0.8113. Min Range: -0.8113

Max Act: 0.6600. Min Act: -0.0000

Data Index: 1158781 (The Pile)

Max Activating Token Index: 236

Text #9

Max Range: 0.8113. Min Range: -0.8113

Max Act: 0.6122. Min Act: -0.0000

Data Index: 1465790 (The Pile)

Max Activating Token Index: 158

Text #10

Max Range: 0.8113. Min Range: -0.8113

Max Act: 0.5968. Min Act: -0.0000

Data Index: 669283 (The Pile)

Max Activating Token Index: 84

Text #11

Max Range: 0.8113. Min Range: -0.8113

Max Act: 0.5852. Min Act: -0.0000

Data Index: 486591 (The Pile)

Max Activating Token Index: 541

Text #12

Max Range: 0.8113. Min Range: -0.8113

Max Act: 0.6019. Min Act: -0.0000

Data Index: 404207 (The Pile)

Max Activating Token Index: 282

Text #13

Max Range: 0.8113. Min Range: -0.8113

Max Act: 0.6392. Min Act: -0.0000

Data Index: 1696509 (The Pile)

Max Activating Token Index: 261

Text #14

Max Range: 0.8113. Min Range: -0.8113

Max Act: 0.5737. Min Act: -0.0000

Data Index: 1976988 (The Pile)

Max Activating Token Index: 188

Text #15

Max Range: 0.8113. Min Range: -0.8113

Max Act: 0.6713. Min Act: -0.0000

Data Index: 1538580 (The Pile)

Max Activating Token Index: 606

Text #16

Max Range: 0.8113. Min Range: -0.8113

Max Act: 0.5840. Min Act: -0.0000

Data Index: 1398657 (The Pile)

Max Activating Token Index: 262

Text #17

Max Range: 0.8113. Min Range: -0.8113

Max Act: 0.5963. Min Act: -0.0000

Data Index: 1870229 (The Pile)

Max Activating Token Index: 304

Text #18

Max Range: 0.8113. Min Range: -0.8113

Max Act: 0.5380. Min Act: -0.0000

Data Index: 617017 (The Pile)

Max Activating Token Index: 302

Text #19

Max Range: 0.8113. Min Range: -0.8113

Max Act: 0.5652. Min Act: -0.0000

Data Index: 1984879 (The Pile)

Max Activating Token Index: 170