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

Dataset: The Pile

Neuron 1046 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: 1.9146. Min Range: -1.9146

Max Act: 1.6852. Min Act: -0.0000

Data Index: 1399685 (The Pile)

Max Activating Token Index: 532

Text #1

Max Range: 1.9146. Min Range: -1.9146

Max Act: 1.8243. Min Act: -0.0000

Data Index: 163922 (The Pile)

Max Activating Token Index: 295

Text #2

Max Range: 1.9146. Min Range: -1.9146

Max Act: 1.9146. Min Act: -0.0000

Data Index: 1290192 (The Pile)

Max Activating Token Index: 682

Text #3

Max Range: 1.9146. Min Range: -1.9146

Max Act: 1.7668. Min Act: -0.0000

Data Index: 1379243 (The Pile)

Max Activating Token Index: 324

Text #4

Max Range: 1.9146. Min Range: -1.9146

Max Act: 1.7098. Min Act: -0.0000

Data Index: 1711600 (The Pile)

Max Activating Token Index: 384

Text #5

Max Range: 1.9146. Min Range: -1.9146

Max Act: 1.5484. Min Act: -0.0000

Data Index: 903374 (The Pile)

Max Activating Token Index: 486

Text #6

Max Range: 1.9146. Min Range: -1.9146

Max Act: 1.6028. Min Act: -0.0000

Data Index: 685860 (The Pile)

Max Activating Token Index: 536

Text #7

Max Range: 1.9146. Min Range: -1.9146

Max Act: 1.6098. Min Act: -0.0000

Data Index: 422978 (The Pile)

Max Activating Token Index: 261

Text #8

Max Range: 1.9146. Min Range: -1.9146

Max Act: 1.5969. Min Act: -0.0000

Data Index: 356374 (The Pile)

Max Activating Token Index: 381

Text #9

Max Range: 1.9146. Min Range: -1.9146

Max Act: 1.5048. Min Act: -0.0000

Data Index: 1540786 (The Pile)

Max Activating Token Index: 404

Text #10

Max Range: 1.9146. Min Range: -1.9146

Max Act: 1.5058. Min Act: -0.0000

Data Index: 1694572 (The Pile)

Max Activating Token Index: 982

Text #11

Max Range: 1.9146. Min Range: -1.9146

Max Act: 1.6018. Min Act: -0.0000

Data Index: 1560048 (The Pile)

Max Activating Token Index: 448

Text #12

Max Range: 1.9146. Min Range: -1.9146

Max Act: 1.4547. Min Act: -0.0000

Data Index: 1215111 (The Pile)

Max Activating Token Index: 977

Text #13

Max Range: 1.9146. Min Range: -1.9146

Max Act: 1.5359. Min Act: -0.0000

Data Index: 1872133 (The Pile)

Max Activating Token Index: 478

Text #14

Max Range: 1.9146. Min Range: -1.9146

Max Act: 1.5379. Min Act: -0.0000

Data Index: 483233 (The Pile)

Max Activating Token Index: 430

Text #15

Max Range: 1.9146. Min Range: -1.9146

Max Act: 1.3711. Min Act: -0.0000

Data Index: 980562 (The Pile)

Max Activating Token Index: 224

Text #16

Max Range: 1.9146. Min Range: -1.9146

Max Act: 1.5397. Min Act: -0.0000

Data Index: 1567908 (The Pile)

Max Activating Token Index: 503

Text #17

Max Range: 1.9146. Min Range: -1.9146

Max Act: 1.4763. Min Act: 0.0000

Data Index: 356947 (The Pile)

Max Activating Token Index: 183

Text #18

Max Range: 1.9146. Min Range: -1.9146

Max Act: 1.5208. Min Act: -0.0000

Data Index: 307051 (The Pile)

Max Activating Token Index: 471

Text #19

Max Range: 1.9146. Min Range: -1.9146

Max Act: 1.5084. Min Act: -0.0000

Data Index: 360144 (The Pile)

Max Activating Token Index: 759