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

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

Neuron 608 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2701. Min Range: -0.2701

Max Act: 0.2652. Min Act: -0.0000

Data Index: 311105 (C4 (Web Text))

Max Activating Token Index: 768

Text #1

Max Range: 0.2701. Min Range: -0.2701

Max Act: 0.2559. Min Act: -0.0000

Data Index: 36328 (C4 (Web Text))

Max Activating Token Index: 785

Text #2

Max Range: 0.2701. Min Range: -0.2701

Max Act: 0.2520. Min Act: -0.0000

Data Index: 333308 (C4 (Web Text))

Max Activating Token Index: 197

Text #3

Max Range: 0.2701. Min Range: -0.2701

Max Act: 0.2701. Min Act: -0.0001

Data Index: 1137707 (C4 (Web Text))

Max Activating Token Index: 98

Text #4

Max Range: 0.2701. Min Range: -0.2701

Max Act: 0.1994. Min Act: -0.0000

Data Index: 1153050 (C4 (Web Text))

Max Activating Token Index: 363

Text #5

Max Range: 0.2701. Min Range: -0.2701

Max Act: 0.1738. Min Act: -0.0000

Data Index: 758727 (C4 (Web Text))

Max Activating Token Index: 378

Text #6

Max Range: 0.2701. Min Range: -0.2701

Max Act: 0.1750. Min Act: -0.0000

Data Index: 252943 (C4 (Web Text))

Max Activating Token Index: 750

Text #7

Max Range: 0.2701. Min Range: -0.2701

Max Act: 0.1526. Min Act: -0.0000

Data Index: 205189 (C4 (Web Text))

Max Activating Token Index: 380

Text #8

Max Range: 0.2701. Min Range: -0.2701

Max Act: 0.1563. Min Act: -0.0000

Data Index: 613848 (C4 (Web Text))

Max Activating Token Index: 929

Text #9

Max Range: 0.2701. Min Range: -0.2701

Max Act: 0.1570. Min Act: -0.0000

Data Index: 28499 (C4 (Web Text))

Max Activating Token Index: 484

Text #10

Max Range: 0.2701. Min Range: -0.2701

Max Act: 0.1542. Min Act: -0.0000

Data Index: 690893 (C4 (Web Text))

Max Activating Token Index: 157

Text #11

Max Range: 0.2701. Min Range: -0.2701

Max Act: 0.1514. Min Act: -0.0000

Data Index: 11897 (C4 (Web Text))

Max Activating Token Index: 17

Text #12

Max Range: 0.2701. Min Range: -0.2701

Max Act: 0.1456. Min Act: -0.0000

Data Index: 425206 (C4 (Web Text))

Max Activating Token Index: 233

Text #13

Max Range: 0.2701. Min Range: -0.2701

Max Act: 0.1266. Min Act: -0.0000

Data Index: 817689 (C4 (Web Text))

Max Activating Token Index: 740

Text #14

Max Range: 0.2701. Min Range: -0.2701

Max Act: 0.1447. Min Act: -0.0000

Data Index: 1117277 (C4 (Web Text))

Max Activating Token Index: 251

Text #15

Max Range: 0.2701. Min Range: -0.2701

Max Act: 0.1412. Min Act: -0.0000

Data Index: 1195843 (C4 (Web Text))

Max Activating Token Index: 242

Text #16

Max Range: 0.2701. Min Range: -0.2701

Max Act: 0.1363. Min Act: -0.0000

Data Index: 393250 (C4 (Web Text))

Max Activating Token Index: 61

Text #17

Max Range: 0.2701. Min Range: -0.2701

Max Act: 0.1424. Min Act: -0.0000

Data Index: 1190804 (C4 (Web Text))

Max Activating Token Index: 139

Text #18

Max Range: 0.2701. Min Range: -0.2701

Max Act: 0.1473. Min Act: -0.0000

Data Index: 1365738 (Python Code)

Max Activating Token Index: 214

Text #19

Max Range: 0.2701. Min Range: -0.2701

Max Act: 0.1468. Min Act: -0.0000

Data Index: 637307 (C4 (Web Text))

Max Activating Token Index: 205