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

Dataset: The Pile

Neuron 4359 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: 3.4260. Min Range: -3.4260

Max Act: 3.4260. Min Act: -0.0000

Data Index: 39098 (The Pile)

Max Activating Token Index: 180

Text #1

Max Range: 3.4260. Min Range: -3.4260

Max Act: 3.0017. Min Act: -0.0000

Data Index: 1632953 (The Pile)

Max Activating Token Index: 193

Text #2

Max Range: 3.4260. Min Range: -3.4260

Max Act: 3.1304. Min Act: -0.0000

Data Index: 1635746 (The Pile)

Max Activating Token Index: 189

Text #3

Max Range: 3.4260. Min Range: -3.4260

Max Act: 3.1913. Min Act: -0.0000

Data Index: 491477 (The Pile)

Max Activating Token Index: 178

Text #4

Max Range: 3.4260. Min Range: -3.4260

Max Act: 3.0198. Min Act: -0.0000

Data Index: 817226 (The Pile)

Max Activating Token Index: 124

Text #5

Max Range: 3.4260. Min Range: -3.4260

Max Act: 2.8772. Min Act: -0.0000

Data Index: 279154 (The Pile)

Max Activating Token Index: 151

Text #6

Max Range: 3.4260. Min Range: -3.4260

Max Act: 2.9850. Min Act: -0.0000

Data Index: 509117 (The Pile)

Max Activating Token Index: 197

Text #7

Max Range: 3.4260. Min Range: -3.4260

Max Act: 2.9874. Min Act: -0.0000

Data Index: 998878 (The Pile)

Max Activating Token Index: 396

Text #8

Max Range: 3.4260. Min Range: -3.4260

Max Act: 2.9836. Min Act: -0.0000

Data Index: 651288 (The Pile)

Max Activating Token Index: 116

Text #9

Max Range: 3.4260. Min Range: -3.4260

Max Act: 2.9797. Min Act: -0.0000

Data Index: 1746174 (The Pile)

Max Activating Token Index: 348

Text #10

Max Range: 3.4260. Min Range: -3.4260

Max Act: 2.8002. Min Act: -0.0000

Data Index: 455856 (The Pile)

Max Activating Token Index: 449

Text #11

Max Range: 3.4260. Min Range: -3.4260

Max Act: 2.9479. Min Act: -0.0000

Data Index: 1229113 (The Pile)

Max Activating Token Index: 235

Text #12

Max Range: 3.4260. Min Range: -3.4260

Max Act: 2.7958. Min Act: -0.0000

Data Index: 39582 (The Pile)

Max Activating Token Index: 150

Text #13

Max Range: 3.4260. Min Range: -3.4260

Max Act: 2.9061. Min Act: -0.0000

Data Index: 1329358 (The Pile)

Max Activating Token Index: 145

Text #14

Max Range: 3.4260. Min Range: -3.4260

Max Act: 2.7648. Min Act: -0.0000

Data Index: 27061 (The Pile)

Max Activating Token Index: 133

Text #15

Max Range: 3.4260. Min Range: -3.4260

Max Act: 2.6543. Min Act: -0.0000

Data Index: 1410351 (The Pile)

Max Activating Token Index: 397

Text #16

Max Range: 3.4260. Min Range: -3.4260

Max Act: 2.8877. Min Act: -0.0000

Data Index: 1371189 (The Pile)

Max Activating Token Index: 518

Text #17

Max Range: 3.4260. Min Range: -3.4260

Max Act: 2.8779. Min Act: -0.0000

Data Index: 845432 (The Pile)

Max Activating Token Index: 341

Text #18

Max Range: 3.4260. Min Range: -3.4260

Max Act: 2.8712. Min Act: -0.0000

Data Index: 981286 (The Pile)

Max Activating Token Index: 225

Text #19

Max Range: 3.4260. Min Range: -3.4260

Max Act: 2.7406. Min Act: -0.0000

Data Index: 1317220 (The Pile)

Max Activating Token Index: 72