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

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

Neuron 4400 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 9.2447. Min Range: -9.2447

Max Act: 9.2447. Min Act: -0.0000

Data Index: 985764 (C4 (Web Text))

Max Activating Token Index: 375

Text #1

Max Range: 9.2447. Min Range: -9.2447

Max Act: 7.4756. Min Act: -0.0000

Data Index: 108814 (C4 (Web Text))

Max Activating Token Index: 252

Text #2

Max Range: 9.2447. Min Range: -9.2447

Max Act: 6.3961. Min Act: -0.0000

Data Index: 897396 (C4 (Web Text))

Max Activating Token Index: 956

Text #3

Max Range: 9.2447. Min Range: -9.2447

Max Act: 6.5828. Min Act: -0.0000

Data Index: 501703 (C4 (Web Text))

Max Activating Token Index: 342

Text #4

Max Range: 9.2447. Min Range: -9.2447

Max Act: 6.6112. Min Act: -0.0000

Data Index: 1222888 (C4 (Web Text))

Max Activating Token Index: 315

Text #5

Max Range: 9.2447. Min Range: -9.2447

Max Act: 6.2966. Min Act: -0.0000

Data Index: 465840 (C4 (Web Text))

Max Activating Token Index: 110

Text #6

Max Range: 9.2447. Min Range: -9.2447

Max Act: 5.1645. Min Act: -0.0000

Data Index: 782166 (C4 (Web Text))

Max Activating Token Index: 539

Text #7

Max Range: 9.2447. Min Range: -9.2447

Max Act: 5.6289. Min Act: -0.0000

Data Index: 1228311 (C4 (Web Text))

Max Activating Token Index: 272

Text #8

Max Range: 9.2447. Min Range: -9.2447

Max Act: 5.0609. Min Act: -0.0000

Data Index: 567594 (C4 (Web Text))

Max Activating Token Index: 183

Text #9

Max Range: 9.2447. Min Range: -9.2447

Max Act: 4.8105. Min Act: -0.0000

Data Index: 533368 (C4 (Web Text))

Max Activating Token Index: 676

Text #10

Max Range: 9.2447. Min Range: -9.2447

Max Act: 4.6925. Min Act: -0.0000

Data Index: 1203400 (C4 (Web Text))

Max Activating Token Index: 864

Text #11

Max Range: 9.2447. Min Range: -9.2447

Max Act: 4.3819. Min Act: -0.0000

Data Index: 844048 (C4 (Web Text))

Max Activating Token Index: 520

Text #12

Max Range: 9.2447. Min Range: -9.2447

Max Act: 4.0902. Min Act: -0.0000

Data Index: 231247 (C4 (Web Text))

Max Activating Token Index: 262

Text #13

Max Range: 9.2447. Min Range: -9.2447

Max Act: 4.3761. Min Act: -0.0000

Data Index: 853404 (C4 (Web Text))

Max Activating Token Index: 290

Text #14

Max Range: 9.2447. Min Range: -9.2447

Max Act: 4.1520. Min Act: -0.0000

Data Index: 546756 (C4 (Web Text))

Max Activating Token Index: 684

Text #15

Max Range: 9.2447. Min Range: -9.2447

Max Act: 4.3086. Min Act: -0.0000

Data Index: 527459 (C4 (Web Text))

Max Activating Token Index: 609

Text #16

Max Range: 9.2447. Min Range: -9.2447

Max Act: 3.8152. Min Act: -0.0000

Data Index: 1297371 (C4 (Web Text))

Max Activating Token Index: 277

Text #17

Max Range: 9.2447. Min Range: -9.2447

Max Act: 3.8267. Min Act: -0.0000

Data Index: 539725 (C4 (Web Text))

Max Activating Token Index: 817

Text #18

Max Range: 9.2447. Min Range: -9.2447

Max Act: 3.5939. Min Act: -0.0000

Data Index: 554495 (C4 (Web Text))

Max Activating Token Index: 661

Text #19

Max Range: 9.2447. Min Range: -9.2447

Max Act: 3.7170. Min Act: -0.0000

Data Index: 822695 (C4 (Web Text))

Max Activating Token Index: 235