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

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

Neuron 5322 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: 1.2883. Min Range: -1.2883

Max Act: 1.2883. Min Act: -0.0002

Data Index: 270359 (C4 (Web Text))

Max Activating Token Index: 814

Text #1

Max Range: 1.2883. Min Range: -1.2883

Max Act: 1.2495. Min Act: -0.0002

Data Index: 1111955 (C4 (Web Text))

Max Activating Token Index: 763

Text #2

Max Range: 1.2883. Min Range: -1.2883

Max Act: 1.1882. Min Act: -0.0002

Data Index: 1100033 (C4 (Web Text))

Max Activating Token Index: 616

Text #3

Max Range: 1.2883. Min Range: -1.2883

Max Act: 1.1632. Min Act: -0.0002

Data Index: 1282545 (C4 (Web Text))

Max Activating Token Index: 497

Text #4

Max Range: 1.2883. Min Range: -1.2883

Max Act: 1.1579. Min Act: -0.0002

Data Index: 313441 (C4 (Web Text))

Max Activating Token Index: 906

Text #5

Max Range: 1.2883. Min Range: -1.2883

Max Act: 1.1422. Min Act: -0.0002

Data Index: 605013 (C4 (Web Text))

Max Activating Token Index: 700

Text #6

Max Range: 1.2883. Min Range: -1.2883

Max Act: 1.1550. Min Act: -0.0003

Data Index: 560278 (C4 (Web Text))

Max Activating Token Index: 468

Text #7

Max Range: 1.2883. Min Range: -1.2883

Max Act: 1.1507. Min Act: -0.0002

Data Index: 201584 (C4 (Web Text))

Max Activating Token Index: 635

Text #8

Max Range: 1.2883. Min Range: -1.2883

Max Act: 1.1336. Min Act: -0.0002

Data Index: 870637 (C4 (Web Text))

Max Activating Token Index: 545

Text #9

Max Range: 1.2883. Min Range: -1.2883

Max Act: 1.0984. Min Act: -0.0002

Data Index: 886640 (C4 (Web Text))

Max Activating Token Index: 503

Text #10

Max Range: 1.2883. Min Range: -1.2883

Max Act: 1.1044. Min Act: -0.0002

Data Index: 417847 (C4 (Web Text))

Max Activating Token Index: 257

Text #11

Max Range: 1.2883. Min Range: -1.2883

Max Act: 1.0994. Min Act: -0.0002

Data Index: 1172022 (C4 (Web Text))

Max Activating Token Index: 658

Text #12

Max Range: 1.2883. Min Range: -1.2883

Max Act: 1.1012. Min Act: -0.0002

Data Index: 940454 (C4 (Web Text))

Max Activating Token Index: 774

Text #13

Max Range: 1.2883. Min Range: -1.2883

Max Act: 1.0976. Min Act: -0.0002

Data Index: 188296 (C4 (Web Text))

Max Activating Token Index: 808

Text #14

Max Range: 1.2883. Min Range: -1.2883

Max Act: 1.0709. Min Act: -0.0002

Data Index: 926625 (C4 (Web Text))

Max Activating Token Index: 56

Text #15

Max Range: 1.2883. Min Range: -1.2883

Max Act: 1.0935. Min Act: -0.0003

Data Index: 631520 (C4 (Web Text))

Max Activating Token Index: 330

Text #16

Max Range: 1.2883. Min Range: -1.2883

Max Act: 1.0444. Min Act: -0.0002

Data Index: 421522 (C4 (Web Text))

Max Activating Token Index: 110

Text #17

Max Range: 1.2883. Min Range: -1.2883

Max Act: 1.0507. Min Act: -0.0002

Data Index: 750653 (C4 (Web Text))

Max Activating Token Index: 867

Text #18

Max Range: 1.2883. Min Range: -1.2883

Max Act: 1.0734. Min Act: -0.0002

Data Index: 176681 (C4 (Web Text))

Max Activating Token Index: 69

Text #19

Max Range: 1.2883. Min Range: -1.2883

Max Act: 1.0513. Min Act: -0.0002

Data Index: 132461 (C4 (Web Text))

Max Activating Token Index: 871