Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 829 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0600. Min Act: -0.0003

Data Index: 1256076 (C4 (Web Text))

Max Activating Token Index: 994

Text #1

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0484. Min Act: -0.0003

Data Index: 1340660 (C4 (Web Text))

Max Activating Token Index: 854

Text #2

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0496. Min Act: -0.0003

Data Index: 378516 (C4 (Web Text))

Max Activating Token Index: 566

Text #3

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0433. Min Act: -0.0003

Data Index: 667368 (C4 (Web Text))

Max Activating Token Index: 286

Text #4

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0442. Min Act: -0.0003

Data Index: 79579 (C4 (Web Text))

Max Activating Token Index: 105

Text #5

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0427. Min Act: -0.0003

Data Index: 790427 (C4 (Web Text))

Max Activating Token Index: 708

Text #6

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0428. Min Act: -0.0003

Data Index: 1114360 (C4 (Web Text))

Max Activating Token Index: 681

Text #7

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0440. Min Act: -0.0003

Data Index: 767669 (C4 (Web Text))

Max Activating Token Index: 275

Text #8

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0403. Min Act: -0.0003

Data Index: 472775 (C4 (Web Text))

Max Activating Token Index: 123

Text #9

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0422. Min Act: -0.0003

Data Index: 417560 (C4 (Web Text))

Max Activating Token Index: 17

Text #10

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0417. Min Act: -0.0003

Data Index: 1302029 (C4 (Web Text))

Max Activating Token Index: 753

Text #11

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0421. Min Act: -0.0003

Data Index: 538271 (C4 (Web Text))

Max Activating Token Index: 206

Text #12

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0412. Min Act: -0.0003

Data Index: 307025 (C4 (Web Text))

Max Activating Token Index: 1021

Text #13

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0407. Min Act: -0.0003

Data Index: 1272388 (C4 (Web Text))

Max Activating Token Index: 477

Text #14

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0432. Min Act: -0.0003

Data Index: 709875 (C4 (Web Text))

Max Activating Token Index: 332

Text #15

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0396. Min Act: -0.0003

Data Index: 610306 (C4 (Web Text))

Max Activating Token Index: 643

Text #16

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0405. Min Act: -0.0003

Data Index: 1095089 (C4 (Web Text))

Max Activating Token Index: 452

Text #17

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0370. Min Act: -0.0003

Data Index: 1168183 (C4 (Web Text))

Max Activating Token Index: 687

Text #18

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0402. Min Act: -0.0003

Data Index: 553848 (C4 (Web Text))

Max Activating Token Index: 547

Text #19

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0389. Min Act: -0.0003

Data Index: 395332 (C4 (Web Text))

Max Activating Token Index: 368