Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3135 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0529. Min Range: -0.0529

Max Act: 0.0529. Min Act: -0.0003

Data Index: 1319494 (C4 (Web Text))

Max Activating Token Index: 433

Text #1

Max Range: 0.0529. Min Range: -0.0529

Max Act: 0.0449. Min Act: -0.0003

Data Index: 1307697 (C4 (Web Text))

Max Activating Token Index: 424

Text #2

Max Range: 0.0529. Min Range: -0.0529

Max Act: 0.0386. Min Act: -0.0003

Data Index: 436511 (C4 (Web Text))

Max Activating Token Index: 378

Text #3

Max Range: 0.0529. Min Range: -0.0529

Max Act: 0.0372. Min Act: -0.0002

Data Index: 966715 (C4 (Web Text))

Max Activating Token Index: 237

Text #4

Max Range: 0.0529. Min Range: -0.0529

Max Act: 0.0370. Min Act: -0.0003

Data Index: 34827 (C4 (Web Text))

Max Activating Token Index: 80

Text #5

Max Range: 0.0529. Min Range: -0.0529

Max Act: 0.0369. Min Act: -0.0003

Data Index: 501535 (C4 (Web Text))

Max Activating Token Index: 140

Text #6

Max Range: 0.0529. Min Range: -0.0529

Max Act: 0.0335. Min Act: -0.0003

Data Index: 1278381 (C4 (Web Text))

Max Activating Token Index: 675

Text #7

Max Range: 0.0529. Min Range: -0.0529

Max Act: 0.0352. Min Act: -0.0003

Data Index: 566669 (C4 (Web Text))

Max Activating Token Index: 208

Text #8

Max Range: 0.0529. Min Range: -0.0529

Max Act: 0.0332. Min Act: -0.0003

Data Index: 1065203 (C4 (Web Text))

Max Activating Token Index: 405

Text #9

Max Range: 0.0529. Min Range: -0.0529

Max Act: 0.0351. Min Act: -0.0003

Data Index: 1114985 (C4 (Web Text))

Max Activating Token Index: 120

Text #10

Max Range: 0.0529. Min Range: -0.0529

Max Act: 0.0347. Min Act: -0.0003

Data Index: 774562 (C4 (Web Text))

Max Activating Token Index: 504

Text #11

Max Range: 0.0529. Min Range: -0.0529

Max Act: 0.0342. Min Act: -0.0003

Data Index: 735454 (C4 (Web Text))

Max Activating Token Index: 56

Text #12

Max Range: 0.0529. Min Range: -0.0529

Max Act: 0.0333. Min Act: -0.0003

Data Index: 332490 (C4 (Web Text))

Max Activating Token Index: 117

Text #13

Max Range: 0.0529. Min Range: -0.0529

Max Act: 0.0334. Min Act: -0.0003

Data Index: 1032506 (C4 (Web Text))

Max Activating Token Index: 127

Text #14

Max Range: 0.0529. Min Range: -0.0529

Max Act: 0.0331. Min Act: -0.0002

Data Index: 1194171 (C4 (Web Text))

Max Activating Token Index: 389

Text #15

Max Range: 0.0529. Min Range: -0.0529

Max Act: 0.0327. Min Act: -0.0003

Data Index: 886263 (C4 (Web Text))

Max Activating Token Index: 167

Text #16

Max Range: 0.0529. Min Range: -0.0529

Max Act: 0.0321. Min Act: -0.0003

Data Index: 547455 (C4 (Web Text))

Max Activating Token Index: 862

Text #17

Max Range: 0.0529. Min Range: -0.0529

Max Act: 0.0324. Min Act: -0.0003

Data Index: 63186 (C4 (Web Text))

Max Activating Token Index: 684

Text #18

Max Range: 0.0529. Min Range: -0.0529

Max Act: 0.0322. Min Act: -0.0003

Data Index: 95584 (C4 (Web Text))

Max Activating Token Index: 699

Text #19

Max Range: 0.0529. Min Range: -0.0529

Max Act: 0.0313. Min Act: -0.0003

Data Index: 626440 (C4 (Web Text))

Max Activating Token Index: 174