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

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

Neuron 3946 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: 2.1595. Min Range: -2.1595

Max Act: 2.1595. Min Act: -0.0000

Data Index: 1052747 (C4 (Web Text))

Max Activating Token Index: 112

Text #1

Max Range: 2.1595. Min Range: -2.1595

Max Act: 1.9977. Min Act: -0.0000

Data Index: 970617 (C4 (Web Text))

Max Activating Token Index: 892

Text #2

Max Range: 2.1595. Min Range: -2.1595

Max Act: 2.0397. Min Act: -0.0000

Data Index: 28613 (C4 (Web Text))

Max Activating Token Index: 59

Text #3

Max Range: 2.1595. Min Range: -2.1595

Max Act: 1.6475. Min Act: -0.0000

Data Index: 1150407 (C4 (Web Text))

Max Activating Token Index: 811

Text #4

Max Range: 2.1595. Min Range: -2.1595

Max Act: 1.6563. Min Act: -0.0000

Data Index: 328285 (C4 (Web Text))

Max Activating Token Index: 534

Text #5

Max Range: 2.1595. Min Range: -2.1595

Max Act: 1.6365. Min Act: -0.0000

Data Index: 937249 (C4 (Web Text))

Max Activating Token Index: 465

Text #6

Max Range: 2.1595. Min Range: -2.1595

Max Act: 1.4349. Min Act: -0.0000

Data Index: 997212 (C4 (Web Text))

Max Activating Token Index: 714

Text #7

Max Range: 2.1595. Min Range: -2.1595

Max Act: 1.6165. Min Act: -0.0000

Data Index: 465645 (C4 (Web Text))

Max Activating Token Index: 325

Text #8

Max Range: 2.1595. Min Range: -2.1595

Max Act: 1.5113. Min Act: -0.0000

Data Index: 88298 (C4 (Web Text))

Max Activating Token Index: 765

Text #9

Max Range: 2.1595. Min Range: -2.1595

Max Act: 1.5015. Min Act: -0.0000

Data Index: 1326716 (C4 (Web Text))

Max Activating Token Index: 923

Text #10

Max Range: 2.1595. Min Range: -2.1595

Max Act: 1.3062. Min Act: -0.0000

Data Index: 774290 (C4 (Web Text))

Max Activating Token Index: 173

Text #11

Max Range: 2.1595. Min Range: -2.1595

Max Act: 1.3440. Min Act: -0.0000

Data Index: 463629 (C4 (Web Text))

Max Activating Token Index: 465

Text #12

Max Range: 2.1595. Min Range: -2.1595

Max Act: 1.3405. Min Act: -0.0000

Data Index: 662311 (C4 (Web Text))

Max Activating Token Index: 518

Text #13

Max Range: 2.1595. Min Range: -2.1595

Max Act: 1.4545. Min Act: -0.0000

Data Index: 1344346 (C4 (Web Text))

Max Activating Token Index: 704

Text #14

Max Range: 2.1595. Min Range: -2.1595

Max Act: 1.3226. Min Act: -0.0000

Data Index: 994928 (C4 (Web Text))

Max Activating Token Index: 458

Text #15

Max Range: 2.1595. Min Range: -2.1595

Max Act: 1.3619. Min Act: -0.0000

Data Index: 1330869 (C4 (Web Text))

Max Activating Token Index: 657

Text #16

Max Range: 2.1595. Min Range: -2.1595

Max Act: 1.2845. Min Act: -0.0000

Data Index: 709556 (C4 (Web Text))

Max Activating Token Index: 641

Text #17

Max Range: 2.1595. Min Range: -2.1595

Max Act: 1.4242. Min Act: -0.0000

Data Index: 632879 (C4 (Web Text))

Max Activating Token Index: 280

Text #18

Max Range: 2.1595. Min Range: -2.1595

Max Act: 1.2974. Min Act: -0.0000

Data Index: 1250749 (C4 (Web Text))

Max Activating Token Index: 378

Text #19

Max Range: 2.1595. Min Range: -2.1595

Max Act: 1.3186. Min Act: -0.0000

Data Index: 351670 (C4 (Web Text))

Max Activating Token Index: 86