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

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

Neuron 2163 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: 3.8604. Min Range: -3.8604

Max Act: 3.8604. Min Act: -0.0000

Data Index: 75067 (C4 (Web Text))

Max Activating Token Index: 549

Text #1

Max Range: 3.8604. Min Range: -3.8604

Max Act: 3.3887. Min Act: -0.0000

Data Index: 245940 (C4 (Web Text))

Max Activating Token Index: 540

Text #2

Max Range: 3.8604. Min Range: -3.8604

Max Act: 3.0736. Min Act: -0.0000

Data Index: 318617 (C4 (Web Text))

Max Activating Token Index: 248

Text #3

Max Range: 3.8604. Min Range: -3.8604

Max Act: 3.0153. Min Act: -0.0000

Data Index: 567388 (C4 (Web Text))

Max Activating Token Index: 373

Text #4

Max Range: 3.8604. Min Range: -3.8604

Max Act: 2.8898. Min Act: -0.0000

Data Index: 555902 (C4 (Web Text))

Max Activating Token Index: 229

Text #5

Max Range: 3.8604. Min Range: -3.8604

Max Act: 3.1459. Min Act: -0.0000

Data Index: 203339 (C4 (Web Text))

Max Activating Token Index: 468

Text #6

Max Range: 3.8604. Min Range: -3.8604

Max Act: 2.9730. Min Act: -0.0000

Data Index: 1298701 (C4 (Web Text))

Max Activating Token Index: 258

Text #7

Max Range: 3.8604. Min Range: -3.8604

Max Act: 3.0840. Min Act: -0.0000

Data Index: 363823 (C4 (Web Text))

Max Activating Token Index: 617

Text #8

Max Range: 3.8604. Min Range: -3.8604

Max Act: 3.2071. Min Act: -0.0000

Data Index: 545494 (C4 (Web Text))

Max Activating Token Index: 745

Text #9

Max Range: 3.8604. Min Range: -3.8604

Max Act: 3.0198. Min Act: -0.0000

Data Index: 1029697 (C4 (Web Text))

Max Activating Token Index: 634

Text #10

Max Range: 3.8604. Min Range: -3.8604

Max Act: 2.8587. Min Act: -0.0000

Data Index: 999875 (C4 (Web Text))

Max Activating Token Index: 636

Text #11

Max Range: 3.8604. Min Range: -3.8604

Max Act: 3.1237. Min Act: -0.0000

Data Index: 1011666 (C4 (Web Text))

Max Activating Token Index: 768

Text #12

Max Range: 3.8604. Min Range: -3.8604

Max Act: 2.8171. Min Act: -0.0000

Data Index: 352067 (C4 (Web Text))

Max Activating Token Index: 478

Text #13

Max Range: 3.8604. Min Range: -3.8604

Max Act: 2.9071. Min Act: -0.0000

Data Index: 1189852 (C4 (Web Text))

Max Activating Token Index: 958

Text #14

Max Range: 3.8604. Min Range: -3.8604

Max Act: 2.9084. Min Act: -0.0000

Data Index: 839648 (C4 (Web Text))

Max Activating Token Index: 840

Text #15

Max Range: 3.8604. Min Range: -3.8604

Max Act: 2.7327. Min Act: -0.0000

Data Index: 834558 (C4 (Web Text))

Max Activating Token Index: 813

Text #16

Max Range: 3.8604. Min Range: -3.8604

Max Act: 2.8554. Min Act: -0.0000

Data Index: 1085834 (C4 (Web Text))

Max Activating Token Index: 461

Text #17

Max Range: 3.8604. Min Range: -3.8604

Max Act: 2.7053. Min Act: -0.0000

Data Index: 31408 (C4 (Web Text))

Max Activating Token Index: 953

Text #18

Max Range: 3.8604. Min Range: -3.8604

Max Act: 2.8113. Min Act: -0.0000

Data Index: 1014065 (C4 (Web Text))

Max Activating Token Index: 131

Text #19

Max Range: 3.8604. Min Range: -3.8604

Max Act: 2.8147. Min Act: -0.0000

Data Index: 1194479 (C4 (Web Text))

Max Activating Token Index: 521