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

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

Neuron 3959 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: 0.4677. Min Range: -0.4677

Max Act: 0.4677. Min Act: -0.0000

Data Index: 534579 (C4 (Web Text))

Max Activating Token Index: 337

Text #1

Max Range: 0.4677. Min Range: -0.4677

Max Act: 0.4123. Min Act: -0.0000

Data Index: 708576 (C4 (Web Text))

Max Activating Token Index: 999

Text #2

Max Range: 0.4677. Min Range: -0.4677

Max Act: 0.3777. Min Act: -0.0000

Data Index: 1078126 (C4 (Web Text))

Max Activating Token Index: 155

Text #3

Max Range: 0.4677. Min Range: -0.4677

Max Act: 0.3456. Min Act: -0.0000

Data Index: 886406 (C4 (Web Text))

Max Activating Token Index: 973

Text #4

Max Range: 0.4677. Min Range: -0.4677

Max Act: 0.3560. Min Act: -0.0000

Data Index: 1026988 (C4 (Web Text))

Max Activating Token Index: 996

Text #5

Max Range: 0.4677. Min Range: -0.4677

Max Act: 0.3399. Min Act: -0.0000

Data Index: 29132 (C4 (Web Text))

Max Activating Token Index: 432

Text #6

Max Range: 0.4677. Min Range: -0.4677

Max Act: 0.3362. Min Act: -0.0000

Data Index: 1236699 (C4 (Web Text))

Max Activating Token Index: 774

Text #7

Max Range: 0.4677. Min Range: -0.4677

Max Act: 0.3776. Min Act: -0.0000

Data Index: 92253 (C4 (Web Text))

Max Activating Token Index: 564

Text #8

Max Range: 0.4677. Min Range: -0.4677

Max Act: 0.3306. Min Act: -0.0000

Data Index: 210161 (C4 (Web Text))

Max Activating Token Index: 258

Text #9

Max Range: 0.4677. Min Range: -0.4677

Max Act: 0.3432. Min Act: -0.0000

Data Index: 593482 (C4 (Web Text))

Max Activating Token Index: 508

Text #10

Max Range: 0.4677. Min Range: -0.4677

Max Act: 0.3282. Min Act: -0.0000

Data Index: 472734 (C4 (Web Text))

Max Activating Token Index: 519

Text #11

Max Range: 0.4677. Min Range: -0.4677

Max Act: 0.3148. Min Act: -0.0000

Data Index: 430393 (C4 (Web Text))

Max Activating Token Index: 900

Text #12

Max Range: 0.4677. Min Range: -0.4677

Max Act: 0.3184. Min Act: -0.0000

Data Index: 912024 (C4 (Web Text))

Max Activating Token Index: 907

Text #13

Max Range: 0.4677. Min Range: -0.4677

Max Act: 0.2975. Min Act: -0.0000

Data Index: 76012 (C4 (Web Text))

Max Activating Token Index: 296

Text #14

Max Range: 0.4677. Min Range: -0.4677

Max Act: 0.3292. Min Act: -0.0000

Data Index: 335947 (C4 (Web Text))

Max Activating Token Index: 668

Text #15

Max Range: 0.4677. Min Range: -0.4677

Max Act: 0.3301. Min Act: -0.0000

Data Index: 723084 (C4 (Web Text))

Max Activating Token Index: 678

Text #16

Max Range: 0.4677. Min Range: -0.4677

Max Act: 0.3193. Min Act: -0.0000

Data Index: 1331186 (C4 (Web Text))

Max Activating Token Index: 599

Text #17

Max Range: 0.4677. Min Range: -0.4677

Max Act: 0.3191. Min Act: -0.0000

Data Index: 1031591 (C4 (Web Text))

Max Activating Token Index: 766

Text #18

Max Range: 0.4677. Min Range: -0.4677

Max Act: 0.3145. Min Act: -0.0000

Data Index: 773465 (C4 (Web Text))

Max Activating Token Index: 598

Text #19

Max Range: 0.4677. Min Range: -0.4677

Max Act: 0.3280. Min Act: -0.0000

Data Index: 941507 (C4 (Web Text))

Max Activating Token Index: 195