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

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

Neuron 4139 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: 2.3940. Min Range: -2.3940

Max Act: 2.3940. Min Act: -0.0000

Data Index: 488287 (C4 (Web Text))

Max Activating Token Index: 564

Text #1

Max Range: 2.3940. Min Range: -2.3940

Max Act: 1.8340. Min Act: -0.0000

Data Index: 276499 (C4 (Web Text))

Max Activating Token Index: 472

Text #2

Max Range: 2.3940. Min Range: -2.3940

Max Act: 1.5366. Min Act: -0.0000

Data Index: 1218743 (C4 (Web Text))

Max Activating Token Index: 968

Text #3

Max Range: 2.3940. Min Range: -2.3940

Max Act: 1.6915. Min Act: -0.0000

Data Index: 539861 (C4 (Web Text))

Max Activating Token Index: 498

Text #4

Max Range: 2.3940. Min Range: -2.3940

Max Act: 1.5708. Min Act: -0.0000

Data Index: 369747 (C4 (Web Text))

Max Activating Token Index: 876

Text #5

Max Range: 2.3940. Min Range: -2.3940

Max Act: 1.5503. Min Act: -0.0000

Data Index: 837618 (C4 (Web Text))

Max Activating Token Index: 165

Text #6

Max Range: 2.3940. Min Range: -2.3940

Max Act: 1.5404. Min Act: -0.0000

Data Index: 998587 (C4 (Web Text))

Max Activating Token Index: 481

Text #7

Max Range: 2.3940. Min Range: -2.3940

Max Act: 1.4302. Min Act: -0.0000

Data Index: 754572 (C4 (Web Text))

Max Activating Token Index: 264

Text #8

Max Range: 2.3940. Min Range: -2.3940

Max Act: 1.5911. Min Act: -0.0000

Data Index: 150659 (C4 (Web Text))

Max Activating Token Index: 702

Text #9

Max Range: 2.3940. Min Range: -2.3940

Max Act: 1.3499. Min Act: -0.0000

Data Index: 114379 (C4 (Web Text))

Max Activating Token Index: 187

Text #10

Max Range: 2.3940. Min Range: -2.3940

Max Act: 1.4413. Min Act: -0.0000

Data Index: 437695 (C4 (Web Text))

Max Activating Token Index: 699

Text #11

Max Range: 2.3940. Min Range: -2.3940

Max Act: 1.5605. Min Act: -0.0000

Data Index: 179491 (C4 (Web Text))

Max Activating Token Index: 412

Text #12

Max Range: 2.3940. Min Range: -2.3940

Max Act: 1.3687. Min Act: -0.0000

Data Index: 242763 (C4 (Web Text))

Max Activating Token Index: 116

Text #13

Max Range: 2.3940. Min Range: -2.3940

Max Act: 1.4595. Min Act: -0.0000

Data Index: 299925 (C4 (Web Text))

Max Activating Token Index: 625

Text #14

Max Range: 2.3940. Min Range: -2.3940

Max Act: 1.3867. Min Act: -0.0000

Data Index: 877061 (C4 (Web Text))

Max Activating Token Index: 545

Text #15

Max Range: 2.3940. Min Range: -2.3940

Max Act: 1.3888. Min Act: -0.0000

Data Index: 717528 (C4 (Web Text))

Max Activating Token Index: 407

Text #16

Max Range: 2.3940. Min Range: -2.3940

Max Act: 1.4787. Min Act: -0.0000

Data Index: 1358944 (C4 (Web Text))

Max Activating Token Index: 1019

Text #17

Max Range: 2.3940. Min Range: -2.3940

Max Act: 1.4040. Min Act: -0.0000

Data Index: 65172 (C4 (Web Text))

Max Activating Token Index: 316

Text #18

Max Range: 2.3940. Min Range: -2.3940

Max Act: 1.3989. Min Act: -0.0000

Data Index: 385214 (C4 (Web Text))

Max Activating Token Index: 411

Text #19

Max Range: 2.3940. Min Range: -2.3940

Max Act: 1.3763. Min Act: -0.0000

Data Index: 808125 (C4 (Web Text))

Max Activating Token Index: 101