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

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

Neuron 5521 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1586. Min Range: -1.1586

Max Act: 1.1586. Min Act: -0.0000

Data Index: 1215903 (C4 (Web Text))

Max Activating Token Index: 178

Text #1

Max Range: 1.1586. Min Range: -1.1586

Max Act: 1.1446. Min Act: -0.0000

Data Index: 813362 (C4 (Web Text))

Max Activating Token Index: 454

Text #2

Max Range: 1.1586. Min Range: -1.1586

Max Act: 1.0849. Min Act: -0.0000

Data Index: 869389 (C4 (Web Text))

Max Activating Token Index: 134

Text #3

Max Range: 1.1586. Min Range: -1.1586

Max Act: 1.1456. Min Act: -0.0000

Data Index: 1217046 (C4 (Web Text))

Max Activating Token Index: 48

Text #4

Max Range: 1.1586. Min Range: -1.1586

Max Act: 1.0765. Min Act: -0.0001

Data Index: 56540 (C4 (Web Text))

Max Activating Token Index: 398

Text #5

Max Range: 1.1586. Min Range: -1.1586

Max Act: 1.0816. Min Act: -0.0000

Data Index: 756339 (C4 (Web Text))

Max Activating Token Index: 909

Text #6

Max Range: 1.1586. Min Range: -1.1586

Max Act: 1.0810. Min Act: -0.0000

Data Index: 477398 (C4 (Web Text))

Max Activating Token Index: 438

Text #7

Max Range: 1.1586. Min Range: -1.1586

Max Act: 1.1313. Min Act: -0.0001

Data Index: 504714 (C4 (Web Text))

Max Activating Token Index: 646

Text #8

Max Range: 1.1586. Min Range: -1.1586

Max Act: 1.1022. Min Act: -0.0000

Data Index: 869073 (C4 (Web Text))

Max Activating Token Index: 1004

Text #9

Max Range: 1.1586. Min Range: -1.1586

Max Act: 1.0400. Min Act: -0.0000

Data Index: 451631 (C4 (Web Text))

Max Activating Token Index: 438

Text #10

Max Range: 1.1586. Min Range: -1.1586

Max Act: 1.0166. Min Act: -0.0000

Data Index: 496492 (C4 (Web Text))

Max Activating Token Index: 96

Text #11

Max Range: 1.1586. Min Range: -1.1586

Max Act: 1.0485. Min Act: -0.0000

Data Index: 341865 (C4 (Web Text))

Max Activating Token Index: 113

Text #12

Max Range: 1.1586. Min Range: -1.1586

Max Act: 1.0602. Min Act: -0.0000

Data Index: 661376 (C4 (Web Text))

Max Activating Token Index: 151

Text #13

Max Range: 1.1586. Min Range: -1.1586

Max Act: 0.9929. Min Act: -0.0000

Data Index: 1006420 (C4 (Web Text))

Max Activating Token Index: 515

Text #14

Max Range: 1.1586. Min Range: -1.1586

Max Act: 1.0813. Min Act: -0.0000

Data Index: 876561 (C4 (Web Text))

Max Activating Token Index: 246

Text #15

Max Range: 1.1586. Min Range: -1.1586

Max Act: 0.9889. Min Act: -0.0000

Data Index: 853785 (C4 (Web Text))

Max Activating Token Index: 381

Text #16

Max Range: 1.1586. Min Range: -1.1586

Max Act: 1.0170. Min Act: -0.0001

Data Index: 960497 (C4 (Web Text))

Max Activating Token Index: 910

Text #17

Max Range: 1.1586. Min Range: -1.1586

Max Act: 0.9775. Min Act: -0.0000

Data Index: 77361 (C4 (Web Text))

Max Activating Token Index: 515

Text #18

Max Range: 1.1586. Min Range: -1.1586

Max Act: 1.0240. Min Act: -0.0001

Data Index: 617584 (C4 (Web Text))

Max Activating Token Index: 676

Text #19

Max Range: 1.1586. Min Range: -1.1586

Max Act: 0.8977. Min Act: -0.0000

Data Index: 332339 (C4 (Web Text))

Max Activating Token Index: 338