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

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

Neuron 632 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4098. Min Range: -2.4098

Max Act: 2.4098. Min Act: -0.0000

Data Index: 689246 (C4 (Web Text))

Max Activating Token Index: 945

Text #1

Max Range: 2.4098. Min Range: -2.4098

Max Act: 1.6659. Min Act: -0.0000

Data Index: 1174254 (C4 (Web Text))

Max Activating Token Index: 801

Text #2

Max Range: 2.4098. Min Range: -2.4098

Max Act: 1.5298. Min Act: -0.0000

Data Index: 637723 (C4 (Web Text))

Max Activating Token Index: 40

Text #3

Max Range: 2.4098. Min Range: -2.4098

Max Act: 1.4408. Min Act: -0.0000

Data Index: 264034 (C4 (Web Text))

Max Activating Token Index: 221

Text #4

Max Range: 2.4098. Min Range: -2.4098

Max Act: 1.4113. Min Act: -0.0000

Data Index: 666478 (C4 (Web Text))

Max Activating Token Index: 327

Text #5

Max Range: 2.4098. Min Range: -2.4098

Max Act: 1.2834. Min Act: -0.0000

Data Index: 610920 (C4 (Web Text))

Max Activating Token Index: 50

Text #6

Max Range: 2.4098. Min Range: -2.4098

Max Act: 1.2743. Min Act: -0.0000

Data Index: 79505 (C4 (Web Text))

Max Activating Token Index: 424

Text #7

Max Range: 2.4098. Min Range: -2.4098

Max Act: 1.2514. Min Act: -0.0000

Data Index: 1052 (C4 (Web Text))

Max Activating Token Index: 762

Text #8

Max Range: 2.4098. Min Range: -2.4098

Max Act: 1.2670. Min Act: -0.0000

Data Index: 911282 (C4 (Web Text))

Max Activating Token Index: 693

Text #9

Max Range: 2.4098. Min Range: -2.4098

Max Act: 1.2428. Min Act: -0.0000

Data Index: 455189 (C4 (Web Text))

Max Activating Token Index: 906

Text #10

Max Range: 2.4098. Min Range: -2.4098

Max Act: 1.2545. Min Act: -0.0000

Data Index: 956518 (C4 (Web Text))

Max Activating Token Index: 93

Text #11

Max Range: 2.4098. Min Range: -2.4098

Max Act: 1.1932. Min Act: -0.0000

Data Index: 1222139 (C4 (Web Text))

Max Activating Token Index: 395

Text #12

Max Range: 2.4098. Min Range: -2.4098

Max Act: 1.2322. Min Act: -0.0000

Data Index: 230807 (C4 (Web Text))

Max Activating Token Index: 549

Text #13

Max Range: 2.4098. Min Range: -2.4098

Max Act: 1.2140. Min Act: -0.0000

Data Index: 463393 (C4 (Web Text))

Max Activating Token Index: 415

Text #14

Max Range: 2.4098. Min Range: -2.4098

Max Act: 1.1020. Min Act: -0.0000

Data Index: 1316049 (C4 (Web Text))

Max Activating Token Index: 192

Text #15

Max Range: 2.4098. Min Range: -2.4098

Max Act: 1.1397. Min Act: -0.0000

Data Index: 770434 (C4 (Web Text))

Max Activating Token Index: 363

Text #16

Max Range: 2.4098. Min Range: -2.4098

Max Act: 1.1474. Min Act: -0.0000

Data Index: 944513 (C4 (Web Text))

Max Activating Token Index: 609

Text #17

Max Range: 2.4098. Min Range: -2.4098

Max Act: 1.1562. Min Act: -0.0000

Data Index: 14377 (C4 (Web Text))

Max Activating Token Index: 454

Text #18

Max Range: 2.4098. Min Range: -2.4098

Max Act: 1.1110. Min Act: -0.0000

Data Index: 929027 (C4 (Web Text))

Max Activating Token Index: 481

Text #19

Max Range: 2.4098. Min Range: -2.4098

Max Act: 1.1363. Min Act: -0.0000

Data Index: 933128 (C4 (Web Text))

Max Activating Token Index: 345