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

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

Neuron 2875 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3883. Min Range: -2.3883

Max Act: 2.3883. Min Act: -0.0001

Data Index: 76120 (C4 (Web Text))

Max Activating Token Index: 928

Text #1

Max Range: 2.3883. Min Range: -2.3883

Max Act: 2.2964. Min Act: -0.0000

Data Index: 848286 (C4 (Web Text))

Max Activating Token Index: 507

Text #2

Max Range: 2.3883. Min Range: -2.3883

Max Act: 2.2681. Min Act: -0.0000

Data Index: 1317145 (C4 (Web Text))

Max Activating Token Index: 91

Text #3

Max Range: 2.3883. Min Range: -2.3883

Max Act: 1.9941. Min Act: -0.0000

Data Index: 543216 (C4 (Web Text))

Max Activating Token Index: 604

Text #4

Max Range: 2.3883. Min Range: -2.3883

Max Act: 2.1624. Min Act: -0.0000

Data Index: 76347 (C4 (Web Text))

Max Activating Token Index: 871

Text #5

Max Range: 2.3883. Min Range: -2.3883

Max Act: 2.2686. Min Act: -0.0000

Data Index: 406739 (C4 (Web Text))

Max Activating Token Index: 477

Text #6

Max Range: 2.3883. Min Range: -2.3883

Max Act: 2.1293. Min Act: -0.0001

Data Index: 947140 (C4 (Web Text))

Max Activating Token Index: 489

Text #7

Max Range: 2.3883. Min Range: -2.3883

Max Act: 1.9112. Min Act: -0.0000

Data Index: 1072255 (C4 (Web Text))

Max Activating Token Index: 369

Text #8

Max Range: 2.3883. Min Range: -2.3883

Max Act: 2.0309. Min Act: -0.0001

Data Index: 386678 (C4 (Web Text))

Max Activating Token Index: 239

Text #9

Max Range: 2.3883. Min Range: -2.3883

Max Act: 2.3304. Min Act: -0.0000

Data Index: 10198 (C4 (Web Text))

Max Activating Token Index: 213

Text #10

Max Range: 2.3883. Min Range: -2.3883

Max Act: 1.8368. Min Act: -0.0000

Data Index: 201718 (C4 (Web Text))

Max Activating Token Index: 587

Text #11

Max Range: 2.3883. Min Range: -2.3883

Max Act: 1.9419. Min Act: -0.0000

Data Index: 218261 (C4 (Web Text))

Max Activating Token Index: 409

Text #12

Max Range: 2.3883. Min Range: -2.3883

Max Act: 2.0233. Min Act: -0.0000

Data Index: 194335 (C4 (Web Text))

Max Activating Token Index: 272

Text #13

Max Range: 2.3883. Min Range: -2.3883

Max Act: 1.9110. Min Act: -0.0000

Data Index: 860268 (C4 (Web Text))

Max Activating Token Index: 81

Text #14

Max Range: 2.3883. Min Range: -2.3883

Max Act: 1.8705. Min Act: -0.0000

Data Index: 605491 (C4 (Web Text))

Max Activating Token Index: 463

Text #15

Max Range: 2.3883. Min Range: -2.3883

Max Act: 1.8797. Min Act: -0.0000

Data Index: 253926 (C4 (Web Text))

Max Activating Token Index: 778

Text #16

Max Range: 2.3883. Min Range: -2.3883

Max Act: 1.7570. Min Act: -0.0000

Data Index: 737787 (C4 (Web Text))

Max Activating Token Index: 348

Text #17

Max Range: 2.3883. Min Range: -2.3883

Max Act: 1.6495. Min Act: -0.0000

Data Index: 1305718 (C4 (Web Text))

Max Activating Token Index: 592

Text #18

Max Range: 2.3883. Min Range: -2.3883

Max Act: 1.8440. Min Act: -0.0000

Data Index: 477344 (C4 (Web Text))

Max Activating Token Index: 516

Text #19

Max Range: 2.3883. Min Range: -2.3883

Max Act: 1.9926. Min Act: -0.0000

Data Index: 1246100 (C4 (Web Text))

Max Activating Token Index: 808