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

Dataset: The Pile

Neuron 1079 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.4231. Min Range: -1.4231

Max Act: 1.3084. Min Act: -0.0000

Data Index: 720627 (The Pile)

Max Activating Token Index: 593

Text #1

Max Range: 1.4231. Min Range: -1.4231

Max Act: 1.4231. Min Act: -0.0000

Data Index: 1430341 (The Pile)

Max Activating Token Index: 474

Text #2

Max Range: 1.4231. Min Range: -1.4231

Max Act: 1.2942. Min Act: -0.0000

Data Index: 81558 (The Pile)

Max Activating Token Index: 331

Text #3

Max Range: 1.4231. Min Range: -1.4231

Max Act: 1.0679. Min Act: -0.0000

Data Index: 1744288 (The Pile)

Max Activating Token Index: 301

Text #4

Max Range: 1.4231. Min Range: -1.4231

Max Act: 0.9933. Min Act: -0.0000

Data Index: 991593 (The Pile)

Max Activating Token Index: 534

Text #5

Max Range: 1.4231. Min Range: -1.4231

Max Act: 0.9521. Min Act: -0.0000

Data Index: 859278 (The Pile)

Max Activating Token Index: 449

Text #6

Max Range: 1.4231. Min Range: -1.4231

Max Act: 0.8902. Min Act: -0.0000

Data Index: 340820 (The Pile)

Max Activating Token Index: 488

Text #7

Max Range: 1.4231. Min Range: -1.4231

Max Act: 0.8848. Min Act: -0.0000

Data Index: 1962991 (The Pile)

Max Activating Token Index: 25

Text #8

Max Range: 1.4231. Min Range: -1.4231

Max Act: 0.8915. Min Act: -0.0000

Data Index: 230677 (The Pile)

Max Activating Token Index: 287

Text #9

Max Range: 1.4231. Min Range: -1.4231

Max Act: 0.8456. Min Act: -0.0000

Data Index: 661263 (The Pile)

Max Activating Token Index: 470

Text #10

Max Range: 1.4231. Min Range: -1.4231

Max Act: 0.8963. Min Act: -0.0000

Data Index: 447364 (The Pile)

Max Activating Token Index: 183

Text #11

Max Range: 1.4231. Min Range: -1.4231

Max Act: 0.8744. Min Act: -0.0000

Data Index: 1484720 (The Pile)

Max Activating Token Index: 279

Text #12

Max Range: 1.4231. Min Range: -1.4231

Max Act: 0.7677. Min Act: -0.0000

Data Index: 819632 (The Pile)

Max Activating Token Index: 664

Text #13

Max Range: 1.4231. Min Range: -1.4231

Max Act: 0.8869. Min Act: -0.0000

Data Index: 1955650 (The Pile)

Max Activating Token Index: 761

Text #14

Max Range: 1.4231. Min Range: -1.4231

Max Act: 0.8261. Min Act: -0.0000

Data Index: 373103 (The Pile)

Max Activating Token Index: 915

Text #15

Max Range: 1.4231. Min Range: -1.4231

Max Act: 0.6535. Min Act: -0.0000

Data Index: 897410 (The Pile)

Max Activating Token Index: 747

Text #16

Max Range: 1.4231. Min Range: -1.4231

Max Act: 0.7200. Min Act: -0.0000

Data Index: 71188 (The Pile)

Max Activating Token Index: 278

Text #17

Max Range: 1.4231. Min Range: -1.4231

Max Act: 0.8261. Min Act: -0.0000

Data Index: 1995225 (The Pile)

Max Activating Token Index: 135

Text #18

Max Range: 1.4231. Min Range: -1.4231

Max Act: 0.7163. Min Act: -0.0000

Data Index: 362700 (The Pile)

Max Activating Token Index: 482

Text #19

Max Range: 1.4231. Min Range: -1.4231

Max Act: 0.7218. Min Act: -0.0000

Data Index: 1879154 (The Pile)

Max Activating Token Index: 446