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

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

Neuron 4258 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4279. Min Range: -2.4279

Max Act: 2.4279. Min Act: -0.0000

Data Index: 983285 (C4 (Web Text))

Max Activating Token Index: 624

Text #1

Max Range: 2.4279. Min Range: -2.4279

Max Act: 2.3145. Min Act: -0.0000

Data Index: 1193558 (C4 (Web Text))

Max Activating Token Index: 22

Text #2

Max Range: 2.4279. Min Range: -2.4279

Max Act: 2.2330. Min Act: -0.0000

Data Index: 316407 (C4 (Web Text))

Max Activating Token Index: 599

Text #3

Max Range: 2.4279. Min Range: -2.4279

Max Act: 2.1115. Min Act: -0.0000

Data Index: 486724 (C4 (Web Text))

Max Activating Token Index: 114

Text #4

Max Range: 2.4279. Min Range: -2.4279

Max Act: 1.8568. Min Act: -0.0000

Data Index: 939519 (C4 (Web Text))

Max Activating Token Index: 287

Text #5

Max Range: 2.4279. Min Range: -2.4279

Max Act: 1.8798. Min Act: -0.0000

Data Index: 998427 (C4 (Web Text))

Max Activating Token Index: 415

Text #6

Max Range: 2.4279. Min Range: -2.4279

Max Act: 1.9431. Min Act: -0.0000

Data Index: 717005 (C4 (Web Text))

Max Activating Token Index: 802

Text #7

Max Range: 2.4279. Min Range: -2.4279

Max Act: 1.7407. Min Act: -0.0000

Data Index: 342717 (C4 (Web Text))

Max Activating Token Index: 716

Text #8

Max Range: 2.4279. Min Range: -2.4279

Max Act: 1.8522. Min Act: -0.0000

Data Index: 265273 (C4 (Web Text))

Max Activating Token Index: 153

Text #9

Max Range: 2.4279. Min Range: -2.4279

Max Act: 1.8386. Min Act: -0.0000

Data Index: 164156 (C4 (Web Text))

Max Activating Token Index: 249

Text #10

Max Range: 2.4279. Min Range: -2.4279

Max Act: 1.7827. Min Act: -0.0000

Data Index: 1198786 (C4 (Web Text))

Max Activating Token Index: 243

Text #11

Max Range: 2.4279. Min Range: -2.4279

Max Act: 1.7247. Min Act: -0.0000

Data Index: 496141 (C4 (Web Text))

Max Activating Token Index: 209

Text #12

Max Range: 2.4279. Min Range: -2.4279

Max Act: 1.7165. Min Act: -0.0000

Data Index: 753177 (C4 (Web Text))

Max Activating Token Index: 208

Text #13

Max Range: 2.4279. Min Range: -2.4279

Max Act: 1.6926. Min Act: -0.0000

Data Index: 875305 (C4 (Web Text))

Max Activating Token Index: 777

Text #14

Max Range: 2.4279. Min Range: -2.4279

Max Act: 1.6910. Min Act: -0.0000

Data Index: 986381 (C4 (Web Text))

Max Activating Token Index: 591

Text #15

Max Range: 2.4279. Min Range: -2.4279

Max Act: 1.6099. Min Act: -0.0000

Data Index: 471446 (C4 (Web Text))

Max Activating Token Index: 879

Text #16

Max Range: 2.4279. Min Range: -2.4279

Max Act: 1.6089. Min Act: -0.0000

Data Index: 789576 (C4 (Web Text))

Max Activating Token Index: 796

Text #17

Max Range: 2.4279. Min Range: -2.4279

Max Act: 1.6020. Min Act: -0.0000

Data Index: 268075 (C4 (Web Text))

Max Activating Token Index: 360

Text #18

Max Range: 2.4279. Min Range: -2.4279

Max Act: 1.4165. Min Act: -0.0000

Data Index: 849640 (C4 (Web Text))

Max Activating Token Index: 764

Text #19

Max Range: 2.4279. Min Range: -2.4279

Max Act: 1.4890. Min Act: -0.0000

Data Index: 939315 (C4 (Web Text))

Max Activating Token Index: 56