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

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

Neuron 2196 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: 1.0630. Min Range: -1.0630

Max Act: 1.0630. Min Act: -0.0000

Data Index: 285277 (C4 (Web Text))

Max Activating Token Index: 615

Text #1

Max Range: 1.0630. Min Range: -1.0630

Max Act: 1.0595. Min Act: -0.0000

Data Index: 343663 (C4 (Web Text))

Max Activating Token Index: 906

Text #2

Max Range: 1.0630. Min Range: -1.0630

Max Act: 0.9659. Min Act: -0.0000

Data Index: 846953 (C4 (Web Text))

Max Activating Token Index: 292

Text #3

Max Range: 1.0630. Min Range: -1.0630

Max Act: 0.9366. Min Act: -0.0000

Data Index: 894935 (C4 (Web Text))

Max Activating Token Index: 579

Text #4

Max Range: 1.0630. Min Range: -1.0630

Max Act: 0.9149. Min Act: -0.0000

Data Index: 704475 (C4 (Web Text))

Max Activating Token Index: 526

Text #5

Max Range: 1.0630. Min Range: -1.0630

Max Act: 0.9386. Min Act: -0.0000

Data Index: 795115 (C4 (Web Text))

Max Activating Token Index: 824

Text #6

Max Range: 1.0630. Min Range: -1.0630

Max Act: 0.9169. Min Act: -0.0000

Data Index: 893905 (C4 (Web Text))

Max Activating Token Index: 830

Text #7

Max Range: 1.0630. Min Range: -1.0630

Max Act: 0.9034. Min Act: -0.0000

Data Index: 37564 (C4 (Web Text))

Max Activating Token Index: 920

Text #8

Max Range: 1.0630. Min Range: -1.0630

Max Act: 0.8724. Min Act: 0.0000

Data Index: 456937 (C4 (Web Text))

Max Activating Token Index: 881

Text #9

Max Range: 1.0630. Min Range: -1.0630

Max Act: 0.9448. Min Act: -0.0000

Data Index: 468850 (C4 (Web Text))

Max Activating Token Index: 435

Text #10

Max Range: 1.0630. Min Range: -1.0630

Max Act: 0.9015. Min Act: -0.0000

Data Index: 1235125 (C4 (Web Text))

Max Activating Token Index: 425

Text #11

Max Range: 1.0630. Min Range: -1.0630

Max Act: 0.8456. Min Act: -0.0000

Data Index: 1234170 (C4 (Web Text))

Max Activating Token Index: 391

Text #12

Max Range: 1.0630. Min Range: -1.0630

Max Act: 0.8548. Min Act: -0.0000

Data Index: 350169 (C4 (Web Text))

Max Activating Token Index: 897

Text #13

Max Range: 1.0630. Min Range: -1.0630

Max Act: 0.8041. Min Act: -0.0000

Data Index: 1346351 (C4 (Web Text))

Max Activating Token Index: 1012

Text #14

Max Range: 1.0630. Min Range: -1.0630

Max Act: 0.8088. Min Act: -0.0000

Data Index: 620504 (C4 (Web Text))

Max Activating Token Index: 943

Text #15

Max Range: 1.0630. Min Range: -1.0630

Max Act: 0.7995. Min Act: -0.0000

Data Index: 542024 (C4 (Web Text))

Max Activating Token Index: 387

Text #16

Max Range: 1.0630. Min Range: -1.0630

Max Act: 0.8120. Min Act: -0.0000

Data Index: 28023 (C4 (Web Text))

Max Activating Token Index: 496

Text #17

Max Range: 1.0630. Min Range: -1.0630

Max Act: 0.7557. Min Act: -0.0000

Data Index: 552705 (C4 (Web Text))

Max Activating Token Index: 536

Text #18

Max Range: 1.0630. Min Range: -1.0630

Max Act: 0.7641. Min Act: -0.0000

Data Index: 226151 (C4 (Web Text))

Max Activating Token Index: 514

Text #19

Max Range: 1.0630. Min Range: -1.0630

Max Act: 0.7941. Min Act: -0.0000

Data Index: 386566 (C4 (Web Text))

Max Activating Token Index: 902