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

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

Neuron 252 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0337. Min Act: -0.0001

Data Index: 54789 (C4 (Web Text))

Max Activating Token Index: 381

Text #1

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0361. Min Act: -0.0001

Data Index: 70172 (C4 (Web Text))

Max Activating Token Index: 289

Text #2

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0348. Min Act: -0.0001

Data Index: 21464 (C4 (Web Text))

Max Activating Token Index: 658

Text #3

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0362. Min Act: -0.0001

Data Index: 568677 (C4 (Web Text))

Max Activating Token Index: 115

Text #4

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0335. Min Act: -0.0001

Data Index: 732903 (C4 (Web Text))

Max Activating Token Index: 498

Text #5

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0315. Min Act: -0.0001

Data Index: 500456 (C4 (Web Text))

Max Activating Token Index: 80

Text #6

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0328. Min Act: -0.0001

Data Index: 693396 (C4 (Web Text))

Max Activating Token Index: 628

Text #7

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0330. Min Act: -0.0001

Data Index: 1078659 (C4 (Web Text))

Max Activating Token Index: 508

Text #8

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0330. Min Act: -0.0001

Data Index: 14985 (C4 (Web Text))

Max Activating Token Index: 906

Text #9

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0313. Min Act: -0.0001

Data Index: 74008 (C4 (Web Text))

Max Activating Token Index: 61

Text #10

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0299. Min Act: -0.0001

Data Index: 911875 (C4 (Web Text))

Max Activating Token Index: 531

Text #11

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0292. Min Act: -0.0001

Data Index: 1005403 (C4 (Web Text))

Max Activating Token Index: 595

Text #12

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0326. Min Act: -0.0001

Data Index: 362506 (C4 (Web Text))

Max Activating Token Index: 751

Text #13

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0292. Min Act: -0.0001

Data Index: 514556 (C4 (Web Text))

Max Activating Token Index: 184

Text #14

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0319. Min Act: -0.0001

Data Index: 642166 (C4 (Web Text))

Max Activating Token Index: 37

Text #15

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0296. Min Act: -0.0001

Data Index: 1183256 (C4 (Web Text))

Max Activating Token Index: 361

Text #16

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0287. Min Act: -0.0001

Data Index: 734848 (C4 (Web Text))

Max Activating Token Index: 103

Text #17

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0248. Min Act: -0.0001

Data Index: 1285640 (C4 (Web Text))

Max Activating Token Index: 129

Text #18

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0318. Min Act: -0.0001

Data Index: 1106117 (C4 (Web Text))

Max Activating Token Index: 108

Text #19

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0283. Min Act: -0.0001

Data Index: 1050134 (C4 (Web Text))

Max Activating Token Index: 148