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

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

Neuron 5782 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: 2.4417. Min Range: -2.4417

Max Act: 2.2202. Min Act: -0.0000

Data Index: 904390 (C4 (Web Text))

Max Activating Token Index: 475

Text #1

Max Range: 2.4417. Min Range: -2.4417

Max Act: 2.4076. Min Act: -0.0000

Data Index: 469617 (C4 (Web Text))

Max Activating Token Index: 440

Text #2

Max Range: 2.4417. Min Range: -2.4417

Max Act: 2.2521. Min Act: -0.0000

Data Index: 978204 (C4 (Web Text))

Max Activating Token Index: 148

Text #3

Max Range: 2.4417. Min Range: -2.4417

Max Act: 2.1074. Min Act: -0.0000

Data Index: 982073 (C4 (Web Text))

Max Activating Token Index: 684

Text #4

Max Range: 2.4417. Min Range: -2.4417

Max Act: 2.2250. Min Act: -0.0000

Data Index: 1208396 (C4 (Web Text))

Max Activating Token Index: 672

Text #5

Max Range: 2.4417. Min Range: -2.4417

Max Act: 2.2159. Min Act: -0.0000

Data Index: 312939 (C4 (Web Text))

Max Activating Token Index: 846

Text #6

Max Range: 2.4417. Min Range: -2.4417

Max Act: 2.4417. Min Act: -0.0000

Data Index: 655780 (C4 (Web Text))

Max Activating Token Index: 212

Text #7

Max Range: 2.4417. Min Range: -2.4417

Max Act: 2.0234. Min Act: -0.0000

Data Index: 1014419 (C4 (Web Text))

Max Activating Token Index: 283

Text #8

Max Range: 2.4417. Min Range: -2.4417

Max Act: 1.9626. Min Act: -0.0000

Data Index: 1635462 (Python Code)

Max Activating Token Index: 797

Text #9

Max Range: 2.4417. Min Range: -2.4417

Max Act: 1.9769. Min Act: -0.0000

Data Index: 1194973 (C4 (Web Text))

Max Activating Token Index: 628

Text #10

Max Range: 2.4417. Min Range: -2.4417

Max Act: 1.9396. Min Act: -0.0000

Data Index: 1349163 (C4 (Web Text))

Max Activating Token Index: 572

Text #11

Max Range: 2.4417. Min Range: -2.4417

Max Act: 1.9385. Min Act: -0.0000

Data Index: 57305 (C4 (Web Text))

Max Activating Token Index: 579

Text #12

Max Range: 2.4417. Min Range: -2.4417

Max Act: 1.7874. Min Act: -0.0000

Data Index: 1269685 (C4 (Web Text))

Max Activating Token Index: 541

Text #13

Max Range: 2.4417. Min Range: -2.4417

Max Act: 1.8845. Min Act: -0.0000

Data Index: 560931 (C4 (Web Text))

Max Activating Token Index: 860

Text #14

Max Range: 2.4417. Min Range: -2.4417

Max Act: 1.8814. Min Act: -0.0000

Data Index: 949535 (C4 (Web Text))

Max Activating Token Index: 17

Text #15

Max Range: 2.4417. Min Range: -2.4417

Max Act: 1.8815. Min Act: -0.0000

Data Index: 907181 (C4 (Web Text))

Max Activating Token Index: 584

Text #16

Max Range: 2.4417. Min Range: -2.4417

Max Act: 1.8486. Min Act: -0.0000

Data Index: 407243 (C4 (Web Text))

Max Activating Token Index: 922

Text #17

Max Range: 2.4417. Min Range: -2.4417

Max Act: 1.8596. Min Act: -0.0000

Data Index: 1038349 (C4 (Web Text))

Max Activating Token Index: 609

Text #18

Max Range: 2.4417. Min Range: -2.4417

Max Act: 1.7520. Min Act: -0.0000

Data Index: 1281315 (C4 (Web Text))

Max Activating Token Index: 405

Text #19

Max Range: 2.4417. Min Range: -2.4417

Max Act: 1.8488. Min Act: -0.0000

Data Index: 109382 (C4 (Web Text))

Max Activating Token Index: 561