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

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

Neuron 2715 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0376. Min Range: -0.0376

Max Act: 0.0368. Min Act: -0.0001

Data Index: 650568 (C4 (Web Text))

Max Activating Token Index: 328

Text #1

Max Range: 0.0376. Min Range: -0.0376

Max Act: 0.0376. Min Act: -0.0001

Data Index: 988792 (C4 (Web Text))

Max Activating Token Index: 384

Text #2

Max Range: 0.0376. Min Range: -0.0376

Max Act: 0.0339. Min Act: -0.0001

Data Index: 838166 (C4 (Web Text))

Max Activating Token Index: 687

Text #3

Max Range: 0.0376. Min Range: -0.0376

Max Act: 0.0310. Min Act: -0.0001

Data Index: 79119 (C4 (Web Text))

Max Activating Token Index: 428

Text #4

Max Range: 0.0376. Min Range: -0.0376

Max Act: 0.0303. Min Act: -0.0001

Data Index: 571136 (C4 (Web Text))

Max Activating Token Index: 647

Text #5

Max Range: 0.0376. Min Range: -0.0376

Max Act: 0.0299. Min Act: -0.0001

Data Index: 1232462 (C4 (Web Text))

Max Activating Token Index: 614

Text #6

Max Range: 0.0376. Min Range: -0.0376

Max Act: 0.0292. Min Act: -0.0001

Data Index: 1354702 (C4 (Web Text))

Max Activating Token Index: 76

Text #7

Max Range: 0.0376. Min Range: -0.0376

Max Act: 0.0309. Min Act: -0.0001

Data Index: 494445 (C4 (Web Text))

Max Activating Token Index: 126

Text #8

Max Range: 0.0376. Min Range: -0.0376

Max Act: 0.0236. Min Act: -0.0001

Data Index: 788016 (C4 (Web Text))

Max Activating Token Index: 841

Text #9

Max Range: 0.0376. Min Range: -0.0376

Max Act: 0.0281. Min Act: -0.0001

Data Index: 420443 (C4 (Web Text))

Max Activating Token Index: 31

Text #10

Max Range: 0.0376. Min Range: -0.0376

Max Act: 0.0280. Min Act: -0.0001

Data Index: 119912 (C4 (Web Text))

Max Activating Token Index: 12

Text #11

Max Range: 0.0376. Min Range: -0.0376

Max Act: 0.0273. Min Act: -0.0001

Data Index: 315856 (C4 (Web Text))

Max Activating Token Index: 602

Text #12

Max Range: 0.0376. Min Range: -0.0376

Max Act: 0.0276. Min Act: -0.0001

Data Index: 575094 (C4 (Web Text))

Max Activating Token Index: 156

Text #13

Max Range: 0.0376. Min Range: -0.0376

Max Act: 0.0284. Min Act: -0.0001

Data Index: 1052424 (C4 (Web Text))

Max Activating Token Index: 289

Text #14

Max Range: 0.0376. Min Range: -0.0376

Max Act: 0.0262. Min Act: -0.0001

Data Index: 694890 (C4 (Web Text))

Max Activating Token Index: 424

Text #15

Max Range: 0.0376. Min Range: -0.0376

Max Act: 0.0266. Min Act: -0.0001

Data Index: 885785 (C4 (Web Text))

Max Activating Token Index: 10

Text #16

Max Range: 0.0376. Min Range: -0.0376

Max Act: 0.0287. Min Act: -0.0001

Data Index: 651763 (C4 (Web Text))

Max Activating Token Index: 56

Text #17

Max Range: 0.0376. Min Range: -0.0376

Max Act: 0.0296. Min Act: -0.0001

Data Index: 136843 (C4 (Web Text))

Max Activating Token Index: 396

Text #18

Max Range: 0.0376. Min Range: -0.0376

Max Act: 0.0245. Min Act: -0.0001

Data Index: 1017747 (C4 (Web Text))

Max Activating Token Index: 799

Text #19

Max Range: 0.0376. Min Range: -0.0376

Max Act: 0.0265. Min Act: -0.0001

Data Index: 1117515 (C4 (Web Text))

Max Activating Token Index: 878