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

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

Neuron 2822 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 2.1323. Min Range: -2.1323

Max Act: 2.1323. Min Act: -0.0002

Data Index: 1014614 (C4 (Web Text))

Max Activating Token Index: 845

Text #1

Max Range: 2.1323. Min Range: -2.1323

Max Act: 2.0397. Min Act: -0.0002

Data Index: 40524 (C4 (Web Text))

Max Activating Token Index: 36

Text #2

Max Range: 2.1323. Min Range: -2.1323

Max Act: 1.9503. Min Act: -0.0002

Data Index: 316599 (C4 (Web Text))

Max Activating Token Index: 395

Text #3

Max Range: 2.1323. Min Range: -2.1323

Max Act: 1.9007. Min Act: -0.0002

Data Index: 804388 (C4 (Web Text))

Max Activating Token Index: 962

Text #4

Max Range: 2.1323. Min Range: -2.1323

Max Act: 1.9401. Min Act: -0.0002

Data Index: 52659 (C4 (Web Text))

Max Activating Token Index: 208

Text #5

Max Range: 2.1323. Min Range: -2.1323

Max Act: 1.8879. Min Act: -0.0002

Data Index: 154372 (C4 (Web Text))

Max Activating Token Index: 876

Text #6

Max Range: 2.1323. Min Range: -2.1323

Max Act: 1.8438. Min Act: -0.0002

Data Index: 1108564 (C4 (Web Text))

Max Activating Token Index: 647

Text #7

Max Range: 2.1323. Min Range: -2.1323

Max Act: 1.8332. Min Act: -0.0002

Data Index: 10725 (C4 (Web Text))

Max Activating Token Index: 309

Text #8

Max Range: 2.1323. Min Range: -2.1323

Max Act: 1.8382. Min Act: -0.0002

Data Index: 140133 (C4 (Web Text))

Max Activating Token Index: 740

Text #9

Max Range: 2.1323. Min Range: -2.1323

Max Act: 1.8280. Min Act: -0.0002

Data Index: 787881 (C4 (Web Text))

Max Activating Token Index: 841

Text #10

Max Range: 2.1323. Min Range: -2.1323

Max Act: 1.8445. Min Act: -0.0002

Data Index: 383735 (C4 (Web Text))

Max Activating Token Index: 335

Text #11

Max Range: 2.1323. Min Range: -2.1323

Max Act: 1.8104. Min Act: -0.0002

Data Index: 830782 (C4 (Web Text))

Max Activating Token Index: 29

Text #12

Max Range: 2.1323. Min Range: -2.1323

Max Act: 1.8147. Min Act: -0.0002

Data Index: 421280 (C4 (Web Text))

Max Activating Token Index: 230

Text #13

Max Range: 2.1323. Min Range: -2.1323

Max Act: 1.7688. Min Act: -0.0002

Data Index: 833172 (C4 (Web Text))

Max Activating Token Index: 542

Text #14

Max Range: 2.1323. Min Range: -2.1323

Max Act: 1.7560. Min Act: -0.0002

Data Index: 969490 (C4 (Web Text))

Max Activating Token Index: 826

Text #15

Max Range: 2.1323. Min Range: -2.1323

Max Act: 1.7467. Min Act: -0.0002

Data Index: 879534 (C4 (Web Text))

Max Activating Token Index: 813

Text #16

Max Range: 2.1323. Min Range: -2.1323

Max Act: 1.7394. Min Act: -0.0002

Data Index: 1274414 (C4 (Web Text))

Max Activating Token Index: 705

Text #17

Max Range: 2.1323. Min Range: -2.1323

Max Act: 1.8338. Min Act: -0.0002

Data Index: 119180 (C4 (Web Text))

Max Activating Token Index: 808

Text #18

Max Range: 2.1323. Min Range: -2.1323

Max Act: 1.7551. Min Act: -0.0002

Data Index: 1103096 (C4 (Web Text))

Max Activating Token Index: 465

Text #19

Max Range: 2.1323. Min Range: -2.1323

Max Act: 1.7617. Min Act: -0.0002

Data Index: 383539 (C4 (Web Text))

Max Activating Token Index: 542