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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3875 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1160. Min Range: -1.1160

Max Act: 1.1160. Min Act: -0.0002

Data Index: 144689 (C4 (Web Text))

Max Activating Token Index: 333

Text #1

Max Range: 1.1160. Min Range: -1.1160

Max Act: 1.0754. Min Act: -0.0002

Data Index: 836729 (C4 (Web Text))

Max Activating Token Index: 146

Text #2

Max Range: 1.1160. Min Range: -1.1160

Max Act: 1.0588. Min Act: -0.0002

Data Index: 857119 (C4 (Web Text))

Max Activating Token Index: 786

Text #3

Max Range: 1.1160. Min Range: -1.1160

Max Act: 1.0444. Min Act: -0.0002

Data Index: 113558 (C4 (Web Text))

Max Activating Token Index: 214

Text #4

Max Range: 1.1160. Min Range: -1.1160

Max Act: 1.0410. Min Act: -0.0002

Data Index: 400447 (C4 (Web Text))

Max Activating Token Index: 375

Text #5

Max Range: 1.1160. Min Range: -1.1160

Max Act: 1.0349. Min Act: -0.0002

Data Index: 259314 (C4 (Web Text))

Max Activating Token Index: 189

Text #6

Max Range: 1.1160. Min Range: -1.1160

Max Act: 1.0182. Min Act: -0.0002

Data Index: 155677 (C4 (Web Text))

Max Activating Token Index: 664

Text #7

Max Range: 1.1160. Min Range: -1.1160

Max Act: 1.0128. Min Act: -0.0002

Data Index: 328597 (C4 (Web Text))

Max Activating Token Index: 465

Text #8

Max Range: 1.1160. Min Range: -1.1160

Max Act: 1.0355. Min Act: -0.0002

Data Index: 953009 (C4 (Web Text))

Max Activating Token Index: 711

Text #9

Max Range: 1.1160. Min Range: -1.1160

Max Act: 0.9963. Min Act: -0.0002

Data Index: 631592 (C4 (Web Text))

Max Activating Token Index: 210

Text #10

Max Range: 1.1160. Min Range: -1.1160

Max Act: 0.9958. Min Act: -0.0002

Data Index: 411604 (C4 (Web Text))

Max Activating Token Index: 288

Text #11

Max Range: 1.1160. Min Range: -1.1160

Max Act: 0.9559. Min Act: -0.0002

Data Index: 1008221 (C4 (Web Text))

Max Activating Token Index: 687

Text #12

Max Range: 1.1160. Min Range: -1.1160

Max Act: 0.9770. Min Act: -0.0002

Data Index: 916436 (C4 (Web Text))

Max Activating Token Index: 277

Text #13

Max Range: 1.1160. Min Range: -1.1160

Max Act: 0.9493. Min Act: -0.0002

Data Index: 555159 (C4 (Web Text))

Max Activating Token Index: 415

Text #14

Max Range: 1.1160. Min Range: -1.1160

Max Act: 0.9690. Min Act: -0.0002

Data Index: 653944 (C4 (Web Text))

Max Activating Token Index: 595

Text #15

Max Range: 1.1160. Min Range: -1.1160

Max Act: 0.9701. Min Act: -0.0002

Data Index: 746089 (C4 (Web Text))

Max Activating Token Index: 45

Text #16

Max Range: 1.1160. Min Range: -1.1160

Max Act: 0.9526. Min Act: -0.0002

Data Index: 1086415 (C4 (Web Text))

Max Activating Token Index: 712

Text #17

Max Range: 1.1160. Min Range: -1.1160

Max Act: 0.9417. Min Act: -0.0002

Data Index: 1160773 (C4 (Web Text))

Max Activating Token Index: 226

Text #18

Max Range: 1.1160. Min Range: -1.1160

Max Act: 0.9463. Min Act: -0.0002

Data Index: 643105 (C4 (Web Text))

Max Activating Token Index: 121

Text #19

Max Range: 1.1160. Min Range: -1.1160

Max Act: 0.9149. Min Act: -0.0002

Data Index: 698786 (C4 (Web Text))

Max Activating Token Index: 485