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

Dataset: The Pile

Neuron 1306 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: 0.6151. Min Range: -0.6151

Max Act: 0.6151. Min Act: -0.0000

Data Index: 1240766 (The Pile)

Max Activating Token Index: 156

Text #1

Max Range: 0.6151. Min Range: -0.6151

Max Act: 0.5368. Min Act: -0.0000

Data Index: 144398 (The Pile)

Max Activating Token Index: 109

Text #2

Max Range: 0.6151. Min Range: -0.6151

Max Act: 0.4762. Min Act: -0.0000

Data Index: 1770721 (The Pile)

Max Activating Token Index: 191

Text #3

Max Range: 0.6151. Min Range: -0.6151

Max Act: 0.4638. Min Act: -0.0000

Data Index: 417945 (The Pile)

Max Activating Token Index: 953

Text #4

Max Range: 0.6151. Min Range: -0.6151

Max Act: 0.4583. Min Act: -0.0000

Data Index: 298075 (The Pile)

Max Activating Token Index: 347

Text #5

Max Range: 0.6151. Min Range: -0.6151

Max Act: 0.4308. Min Act: -0.0000

Data Index: 1990057 (The Pile)

Max Activating Token Index: 338

Text #6

Max Range: 0.6151. Min Range: -0.6151

Max Act: 0.3908. Min Act: -0.0000

Data Index: 702896 (The Pile)

Max Activating Token Index: 497

Text #7

Max Range: 0.6151. Min Range: -0.6151

Max Act: 0.4219. Min Act: -0.0000

Data Index: 735480 (The Pile)

Max Activating Token Index: 982

Text #8

Max Range: 0.6151. Min Range: -0.6151

Max Act: 0.4230. Min Act: -0.0000

Data Index: 81419 (The Pile)

Max Activating Token Index: 654

Text #9

Max Range: 0.6151. Min Range: -0.6151

Max Act: 0.3807. Min Act: -0.0000

Data Index: 1497138 (The Pile)

Max Activating Token Index: 437

Text #10

Max Range: 0.6151. Min Range: -0.6151

Max Act: 0.4118. Min Act: -0.0000

Data Index: 1728414 (The Pile)

Max Activating Token Index: 1000

Text #11

Max Range: 0.6151. Min Range: -0.6151

Max Act: 0.3991. Min Act: -0.0000

Data Index: 1779728 (The Pile)

Max Activating Token Index: 361

Text #12

Max Range: 0.6151. Min Range: -0.6151

Max Act: 0.3955. Min Act: -0.0000

Data Index: 1445962 (The Pile)

Max Activating Token Index: 222

Text #13

Max Range: 0.6151. Min Range: -0.6151

Max Act: 0.3952. Min Act: -0.0000

Data Index: 509573 (The Pile)

Max Activating Token Index: 444

Text #14

Max Range: 0.6151. Min Range: -0.6151

Max Act: 0.3304. Min Act: -0.0000

Data Index: 189649 (The Pile)

Max Activating Token Index: 547

Text #15

Max Range: 0.6151. Min Range: -0.6151

Max Act: 0.4027. Min Act: -0.0000

Data Index: 1107893 (The Pile)

Max Activating Token Index: 336

Text #16

Max Range: 0.6151. Min Range: -0.6151

Max Act: 0.3805. Min Act: -0.0000

Data Index: 1387399 (The Pile)

Max Activating Token Index: 1007

Text #17

Max Range: 0.6151. Min Range: -0.6151

Max Act: 0.4122. Min Act: -0.0000

Data Index: 1217815 (The Pile)

Max Activating Token Index: 69

Text #18

Max Range: 0.6151. Min Range: -0.6151

Max Act: 0.3780. Min Act: -0.0000

Data Index: 234983 (The Pile)

Max Activating Token Index: 540

Text #19

Max Range: 0.6151. Min Range: -0.6151

Max Act: 0.3794. Min Act: -0.0000

Data Index: 1457397 (The Pile)

Max Activating Token Index: 62