Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5720 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.0319. Min Range: -4.0319

Max Act: 4.0319. Min Act: -0.0000

Data Index: 512354 (C4 (Web Text))

Max Activating Token Index: 59

Text #1

Max Range: 4.0319. Min Range: -4.0319

Max Act: 3.5189. Min Act: -0.0000

Data Index: 441830 (C4 (Web Text))

Max Activating Token Index: 1014

Text #2

Max Range: 4.0319. Min Range: -4.0319

Max Act: 3.2689. Min Act: -0.0000

Data Index: 121463 (C4 (Web Text))

Max Activating Token Index: 415

Text #3

Max Range: 4.0319. Min Range: -4.0319

Max Act: 2.7665. Min Act: -0.0000

Data Index: 1284590 (C4 (Web Text))

Max Activating Token Index: 586

Text #4

Max Range: 4.0319. Min Range: -4.0319

Max Act: 2.9086. Min Act: -0.0000

Data Index: 1122834 (C4 (Web Text))

Max Activating Token Index: 334

Text #5

Max Range: 4.0319. Min Range: -4.0319

Max Act: 3.1219. Min Act: -0.0000

Data Index: 1199893 (C4 (Web Text))

Max Activating Token Index: 421

Text #6

Max Range: 4.0319. Min Range: -4.0319

Max Act: 3.0516. Min Act: -0.0000

Data Index: 246579 (C4 (Web Text))

Max Activating Token Index: 141

Text #7

Max Range: 4.0319. Min Range: -4.0319

Max Act: 3.2123. Min Act: -0.0000

Data Index: 849887 (C4 (Web Text))

Max Activating Token Index: 629

Text #8

Max Range: 4.0319. Min Range: -4.0319

Max Act: 2.6129. Min Act: -0.0000

Data Index: 3943 (C4 (Web Text))

Max Activating Token Index: 654

Text #9

Max Range: 4.0319. Min Range: -4.0319

Max Act: 2.4670. Min Act: -0.0000

Data Index: 940620 (C4 (Web Text))

Max Activating Token Index: 337

Text #10

Max Range: 4.0319. Min Range: -4.0319

Max Act: 2.6122. Min Act: -0.0000

Data Index: 1203710 (C4 (Web Text))

Max Activating Token Index: 51

Text #11

Max Range: 4.0319. Min Range: -4.0319

Max Act: 2.2119. Min Act: -0.0000

Data Index: 806044 (C4 (Web Text))

Max Activating Token Index: 347

Text #12

Max Range: 4.0319. Min Range: -4.0319

Max Act: 2.4152. Min Act: -0.0000

Data Index: 1030092 (C4 (Web Text))

Max Activating Token Index: 460

Text #13

Max Range: 4.0319. Min Range: -4.0319

Max Act: 2.4760. Min Act: -0.0000

Data Index: 946099 (C4 (Web Text))

Max Activating Token Index: 811

Text #14

Max Range: 4.0319. Min Range: -4.0319

Max Act: 2.4677. Min Act: -0.0000

Data Index: 26671 (C4 (Web Text))

Max Activating Token Index: 266

Text #15

Max Range: 4.0319. Min Range: -4.0319

Max Act: 2.5726. Min Act: -0.0000

Data Index: 255474 (C4 (Web Text))

Max Activating Token Index: 773

Text #16

Max Range: 4.0319. Min Range: -4.0319

Max Act: 2.7434. Min Act: -0.0000

Data Index: 105519 (C4 (Web Text))

Max Activating Token Index: 627

Text #17

Max Range: 4.0319. Min Range: -4.0319

Max Act: 2.2272. Min Act: -0.0000

Data Index: 340406 (C4 (Web Text))

Max Activating Token Index: 242

Text #18

Max Range: 4.0319. Min Range: -4.0319

Max Act: 2.2704. Min Act: -0.0000

Data Index: 898729 (C4 (Web Text))

Max Activating Token Index: 532

Text #19

Max Range: 4.0319. Min Range: -4.0319

Max Act: 2.7126. Min Act: -0.0000

Data Index: 431582 (C4 (Web Text))

Max Activating Token Index: 786