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

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

Neuron 1623 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3148. Min Range: -2.3148

Max Act: 2.3148. Min Act: -0.0000

Data Index: 981896 (C4 (Web Text))

Max Activating Token Index: 556

Text #1

Max Range: 2.3148. Min Range: -2.3148

Max Act: 2.0776. Min Act: -0.0000

Data Index: 671510 (C4 (Web Text))

Max Activating Token Index: 181

Text #2

Max Range: 2.3148. Min Range: -2.3148

Max Act: 1.9583. Min Act: -0.0000

Data Index: 128191 (C4 (Web Text))

Max Activating Token Index: 452

Text #3

Max Range: 2.3148. Min Range: -2.3148

Max Act: 1.8643. Min Act: -0.0000

Data Index: 242808 (C4 (Web Text))

Max Activating Token Index: 915

Text #4

Max Range: 2.3148. Min Range: -2.3148

Max Act: 1.8223. Min Act: -0.0000

Data Index: 507582 (C4 (Web Text))

Max Activating Token Index: 141

Text #5

Max Range: 2.3148. Min Range: -2.3148

Max Act: 1.9276. Min Act: -0.0000

Data Index: 923654 (C4 (Web Text))

Max Activating Token Index: 447

Text #6

Max Range: 2.3148. Min Range: -2.3148

Max Act: 1.7199. Min Act: -0.0000

Data Index: 1110628 (C4 (Web Text))

Max Activating Token Index: 150

Text #7

Max Range: 2.3148. Min Range: -2.3148

Max Act: 1.7658. Min Act: -0.0000

Data Index: 584058 (C4 (Web Text))

Max Activating Token Index: 773

Text #8

Max Range: 2.3148. Min Range: -2.3148

Max Act: 1.7297. Min Act: -0.0000

Data Index: 634056 (C4 (Web Text))

Max Activating Token Index: 370

Text #9

Max Range: 2.3148. Min Range: -2.3148

Max Act: 1.7119. Min Act: -0.0000

Data Index: 655139 (C4 (Web Text))

Max Activating Token Index: 409

Text #10

Max Range: 2.3148. Min Range: -2.3148

Max Act: 1.7761. Min Act: -0.0000

Data Index: 1298372 (C4 (Web Text))

Max Activating Token Index: 113

Text #11

Max Range: 2.3148. Min Range: -2.3148

Max Act: 1.6620. Min Act: -0.0000

Data Index: 28407 (C4 (Web Text))

Max Activating Token Index: 561

Text #12

Max Range: 2.3148. Min Range: -2.3148

Max Act: 1.6332. Min Act: -0.0000

Data Index: 40465 (C4 (Web Text))

Max Activating Token Index: 359

Text #13

Max Range: 2.3148. Min Range: -2.3148

Max Act: 1.5831. Min Act: -0.0000

Data Index: 497621 (C4 (Web Text))

Max Activating Token Index: 877

Text #14

Max Range: 2.3148. Min Range: -2.3148

Max Act: 1.5652. Min Act: -0.0000

Data Index: 222448 (C4 (Web Text))

Max Activating Token Index: 556

Text #15

Max Range: 2.3148. Min Range: -2.3148

Max Act: 1.5485. Min Act: -0.0000

Data Index: 959124 (C4 (Web Text))

Max Activating Token Index: 887

Text #16

Max Range: 2.3148. Min Range: -2.3148

Max Act: 1.7055. Min Act: -0.0000

Data Index: 206210 (C4 (Web Text))

Max Activating Token Index: 780

Text #17

Max Range: 2.3148. Min Range: -2.3148

Max Act: 1.4425. Min Act: -0.0000

Data Index: 1173005 (C4 (Web Text))

Max Activating Token Index: 663

Text #18

Max Range: 2.3148. Min Range: -2.3148

Max Act: 1.5075. Min Act: -0.0000

Data Index: 1258357 (C4 (Web Text))

Max Activating Token Index: 562

Text #19

Max Range: 2.3148. Min Range: -2.3148

Max Act: 1.3515. Min Act: -0.0000

Data Index: 632983 (C4 (Web Text))

Max Activating Token Index: 891