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

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

Neuron 4804 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.1688. Min Range: -0.1688

Max Act: 0.1688. Min Act: -0.0001

Data Index: 671828 (C4 (Web Text))

Max Activating Token Index: 98

Text #1

Max Range: 0.1688. Min Range: -0.1688

Max Act: 0.1636. Min Act: -0.0001

Data Index: 352932 (C4 (Web Text))

Max Activating Token Index: 17

Text #2

Max Range: 0.1688. Min Range: -0.1688

Max Act: 0.1480. Min Act: -0.0001

Data Index: 610352 (C4 (Web Text))

Max Activating Token Index: 73

Text #3

Max Range: 0.1688. Min Range: -0.1688

Max Act: 0.1470. Min Act: -0.0001

Data Index: 546814 (C4 (Web Text))

Max Activating Token Index: 148

Text #4

Max Range: 0.1688. Min Range: -0.1688

Max Act: 0.1461. Min Act: -0.0001

Data Index: 173034 (C4 (Web Text))

Max Activating Token Index: 463

Text #5

Max Range: 0.1688. Min Range: -0.1688

Max Act: 0.1438. Min Act: -0.0001

Data Index: 925149 (C4 (Web Text))

Max Activating Token Index: 607

Text #6

Max Range: 0.1688. Min Range: -0.1688

Max Act: 0.1443. Min Act: -0.0001

Data Index: 458755 (C4 (Web Text))

Max Activating Token Index: 836

Text #7

Max Range: 0.1688. Min Range: -0.1688

Max Act: 0.1400. Min Act: -0.0001

Data Index: 538237 (C4 (Web Text))

Max Activating Token Index: 843

Text #8

Max Range: 0.1688. Min Range: -0.1688

Max Act: 0.1381. Min Act: -0.0001

Data Index: 146598 (C4 (Web Text))

Max Activating Token Index: 911

Text #9

Max Range: 0.1688. Min Range: -0.1688

Max Act: 0.1365. Min Act: -0.0001

Data Index: 671534 (C4 (Web Text))

Max Activating Token Index: 55

Text #10

Max Range: 0.1688. Min Range: -0.1688

Max Act: 0.1368. Min Act: -0.0001

Data Index: 273845 (C4 (Web Text))

Max Activating Token Index: 241

Text #11

Max Range: 0.1688. Min Range: -0.1688

Max Act: 0.1352. Min Act: -0.0001

Data Index: 1039910 (C4 (Web Text))

Max Activating Token Index: 29

Text #12

Max Range: 0.1688. Min Range: -0.1688

Max Act: 0.1373. Min Act: -0.0001

Data Index: 716902 (C4 (Web Text))

Max Activating Token Index: 223

Text #13

Max Range: 0.1688. Min Range: -0.1688

Max Act: 0.1357. Min Act: -0.0001

Data Index: 300515 (C4 (Web Text))

Max Activating Token Index: 729

Text #14

Max Range: 0.1688. Min Range: -0.1688

Max Act: 0.1341. Min Act: -0.0001

Data Index: 186326 (C4 (Web Text))

Max Activating Token Index: 30

Text #15

Max Range: 0.1688. Min Range: -0.1688

Max Act: 0.1328. Min Act: -0.0001

Data Index: 349602 (C4 (Web Text))

Max Activating Token Index: 407

Text #16

Max Range: 0.1688. Min Range: -0.1688

Max Act: 0.1358. Min Act: -0.0001

Data Index: 437818 (C4 (Web Text))

Max Activating Token Index: 148

Text #17

Max Range: 0.1688. Min Range: -0.1688

Max Act: 0.1332. Min Act: -0.0001

Data Index: 371338 (C4 (Web Text))

Max Activating Token Index: 69

Text #18

Max Range: 0.1688. Min Range: -0.1688

Max Act: 0.1354. Min Act: -0.0001

Data Index: 1074022 (C4 (Web Text))

Max Activating Token Index: 173

Text #19

Max Range: 0.1688. Min Range: -0.1688

Max Act: 0.1320. Min Act: -0.0001

Data Index: 631032 (C4 (Web Text))

Max Activating Token Index: 588