Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5123 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.2704. Min Range: -2.2704

Max Act: 2.1757. Min Act: -0.0000

Data Index: 810389 (C4 (Web Text))

Max Activating Token Index: 395

Text #1

Max Range: 2.2704. Min Range: -2.2704

Max Act: 2.2704. Min Act: -0.0000

Data Index: 632376 (C4 (Web Text))

Max Activating Token Index: 668

Text #2

Max Range: 2.2704. Min Range: -2.2704

Max Act: 2.1201. Min Act: -0.0000

Data Index: 1151554 (C4 (Web Text))

Max Activating Token Index: 820

Text #3

Max Range: 2.2704. Min Range: -2.2704

Max Act: 2.1066. Min Act: -0.0000

Data Index: 405479 (C4 (Web Text))

Max Activating Token Index: 666

Text #4

Max Range: 2.2704. Min Range: -2.2704

Max Act: 1.8848. Min Act: -0.0000

Data Index: 552983 (C4 (Web Text))

Max Activating Token Index: 339

Text #5

Max Range: 2.2704. Min Range: -2.2704

Max Act: 1.8421. Min Act: -0.0000

Data Index: 733789 (C4 (Web Text))

Max Activating Token Index: 577

Text #6

Max Range: 2.2704. Min Range: -2.2704

Max Act: 1.9349. Min Act: -0.0000

Data Index: 344391 (C4 (Web Text))

Max Activating Token Index: 940

Text #7

Max Range: 2.2704. Min Range: -2.2704

Max Act: 1.7656. Min Act: -0.0000

Data Index: 57194 (C4 (Web Text))

Max Activating Token Index: 192

Text #8

Max Range: 2.2704. Min Range: -2.2704

Max Act: 1.9280. Min Act: -0.0000

Data Index: 152560 (C4 (Web Text))

Max Activating Token Index: 893

Text #9

Max Range: 2.2704. Min Range: -2.2704

Max Act: 1.8161. Min Act: -0.0000

Data Index: 512339 (C4 (Web Text))

Max Activating Token Index: 438

Text #10

Max Range: 2.2704. Min Range: -2.2704

Max Act: 1.8557. Min Act: -0.0000

Data Index: 320583 (C4 (Web Text))

Max Activating Token Index: 16

Text #11

Max Range: 2.2704. Min Range: -2.2704

Max Act: 1.8313. Min Act: -0.0000

Data Index: 1120896 (C4 (Web Text))

Max Activating Token Index: 990

Text #12

Max Range: 2.2704. Min Range: -2.2704

Max Act: 1.8172. Min Act: -0.0000

Data Index: 1032627 (C4 (Web Text))

Max Activating Token Index: 42

Text #13

Max Range: 2.2704. Min Range: -2.2704

Max Act: 1.8033. Min Act: -0.0000

Data Index: 647922 (C4 (Web Text))

Max Activating Token Index: 518

Text #14

Max Range: 2.2704. Min Range: -2.2704

Max Act: 1.7932. Min Act: -0.0000

Data Index: 245313 (C4 (Web Text))

Max Activating Token Index: 926

Text #15

Max Range: 2.2704. Min Range: -2.2704

Max Act: 1.8904. Min Act: -0.0000

Data Index: 214747 (C4 (Web Text))

Max Activating Token Index: 608

Text #16

Max Range: 2.2704. Min Range: -2.2704

Max Act: 1.7945. Min Act: -0.0000

Data Index: 683508 (C4 (Web Text))

Max Activating Token Index: 145

Text #17

Max Range: 2.2704. Min Range: -2.2704

Max Act: 1.7292. Min Act: -0.0000

Data Index: 1457809 (Python Code)

Max Activating Token Index: 313

Text #18

Max Range: 2.2704. Min Range: -2.2704

Max Act: 1.7598. Min Act: -0.0000

Data Index: 438747 (C4 (Web Text))

Max Activating Token Index: 549

Text #19

Max Range: 2.2704. Min Range: -2.2704

Max Act: 1.7129. Min Act: -0.0000

Data Index: 894129 (C4 (Web Text))

Max Activating Token Index: 426