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

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

Neuron 4974 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5403. Min Range: -1.5403

Max Act: 1.5403. Min Act: -0.0000

Data Index: 807979 (C4 (Web Text))

Max Activating Token Index: 130

Text #1

Max Range: 1.5403. Min Range: -1.5403

Max Act: 1.3706. Min Act: -0.0000

Data Index: 383002 (C4 (Web Text))

Max Activating Token Index: 445

Text #2

Max Range: 1.5403. Min Range: -1.5403

Max Act: 1.3618. Min Act: -0.0000

Data Index: 1115579 (C4 (Web Text))

Max Activating Token Index: 318

Text #3

Max Range: 1.5403. Min Range: -1.5403

Max Act: 1.2471. Min Act: -0.0000

Data Index: 233618 (C4 (Web Text))

Max Activating Token Index: 367

Text #4

Max Range: 1.5403. Min Range: -1.5403

Max Act: 1.2189. Min Act: -0.0000

Data Index: 755826 (C4 (Web Text))

Max Activating Token Index: 418

Text #5

Max Range: 1.5403. Min Range: -1.5403

Max Act: 1.1689. Min Act: -0.0000

Data Index: 366898 (C4 (Web Text))

Max Activating Token Index: 903

Text #6

Max Range: 1.5403. Min Range: -1.5403

Max Act: 1.2801. Min Act: -0.0000

Data Index: 726498 (C4 (Web Text))

Max Activating Token Index: 937

Text #7

Max Range: 1.5403. Min Range: -1.5403

Max Act: 1.1457. Min Act: -0.0000

Data Index: 626653 (C4 (Web Text))

Max Activating Token Index: 407

Text #8

Max Range: 1.5403. Min Range: -1.5403

Max Act: 1.2382. Min Act: -0.0000

Data Index: 89886 (C4 (Web Text))

Max Activating Token Index: 194

Text #9

Max Range: 1.5403. Min Range: -1.5403

Max Act: 1.0963. Min Act: -0.0000

Data Index: 171412 (C4 (Web Text))

Max Activating Token Index: 625

Text #10

Max Range: 1.5403. Min Range: -1.5403

Max Act: 1.0847. Min Act: -0.0000

Data Index: 1159440 (C4 (Web Text))

Max Activating Token Index: 349

Text #11

Max Range: 1.5403. Min Range: -1.5403

Max Act: 1.0862. Min Act: -0.0000

Data Index: 704571 (C4 (Web Text))

Max Activating Token Index: 261

Text #12

Max Range: 1.5403. Min Range: -1.5403

Max Act: 1.1224. Min Act: -0.0000

Data Index: 53312 (C4 (Web Text))

Max Activating Token Index: 1004

Text #13

Max Range: 1.5403. Min Range: -1.5403

Max Act: 1.1187. Min Act: -0.0000

Data Index: 1331357 (C4 (Web Text))

Max Activating Token Index: 851

Text #14

Max Range: 1.5403. Min Range: -1.5403

Max Act: 1.1336. Min Act: -0.0000

Data Index: 253562 (C4 (Web Text))

Max Activating Token Index: 595

Text #15

Max Range: 1.5403. Min Range: -1.5403

Max Act: 1.0028. Min Act: -0.0000

Data Index: 858924 (C4 (Web Text))

Max Activating Token Index: 878

Text #16

Max Range: 1.5403. Min Range: -1.5403

Max Act: 1.1500. Min Act: -0.0000

Data Index: 64459 (C4 (Web Text))

Max Activating Token Index: 619

Text #17

Max Range: 1.5403. Min Range: -1.5403

Max Act: 1.0550. Min Act: -0.0000

Data Index: 804220 (C4 (Web Text))

Max Activating Token Index: 470

Text #18

Max Range: 1.5403. Min Range: -1.5403

Max Act: 1.0871. Min Act: -0.0000

Data Index: 787169 (C4 (Web Text))

Max Activating Token Index: 903

Text #19

Max Range: 1.5403. Min Range: -1.5403

Max Act: 0.9892. Min Act: -0.0000

Data Index: 268086 (C4 (Web Text))

Max Activating Token Index: 505