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

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

Neuron 4025 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8346. Min Range: -0.8346

Max Act: 0.8346. Min Act: 0.0000

Data Index: 1576274 (Python Code)

Max Activating Token Index: 529

Text #1

Max Range: 0.8346. Min Range: -0.8346

Max Act: 0.8039. Min Act: -0.0000

Data Index: 1633880 (Python Code)

Max Activating Token Index: 537

Text #2

Max Range: 0.8346. Min Range: -0.8346

Max Act: 0.8298. Min Act: -0.0000

Data Index: 1389846 (Python Code)

Max Activating Token Index: 919

Text #3

Max Range: 0.8346. Min Range: -0.8346

Max Act: 0.8109. Min Act: -0.0000

Data Index: 1457069 (Python Code)

Max Activating Token Index: 980

Text #4

Max Range: 0.8346. Min Range: -0.8346

Max Act: 0.8095. Min Act: -0.0000

Data Index: 1443237 (Python Code)

Max Activating Token Index: 89

Text #5

Max Range: 0.8346. Min Range: -0.8346

Max Act: 0.7879. Min Act: -0.0000

Data Index: 1364812 (Python Code)

Max Activating Token Index: 659

Text #6

Max Range: 0.8346. Min Range: -0.8346

Max Act: 0.7709. Min Act: -0.0000

Data Index: 1641417 (Python Code)

Max Activating Token Index: 284

Text #7

Max Range: 0.8346. Min Range: -0.8346

Max Act: 0.7943. Min Act: -0.0000

Data Index: 1373185 (Python Code)

Max Activating Token Index: 367

Text #8

Max Range: 0.8346. Min Range: -0.8346

Max Act: 0.7663. Min Act: -0.0000

Data Index: 1639498 (Python Code)

Max Activating Token Index: 217

Text #9

Max Range: 0.8346. Min Range: -0.8346

Max Act: 0.7710. Min Act: -0.0000

Data Index: 1418111 (Python Code)

Max Activating Token Index: 323

Text #10

Max Range: 0.8346. Min Range: -0.8346

Max Act: 0.8309. Min Act: 0.0001

Data Index: 1521781 (Python Code)

Max Activating Token Index: 680

Text #11

Max Range: 0.8346. Min Range: -0.8346

Max Act: 0.7598. Min Act: 0.0001

Data Index: 1536452 (Python Code)

Max Activating Token Index: 266

Text #12

Max Range: 0.8346. Min Range: -0.8346

Max Act: 0.7456. Min Act: -0.0000

Data Index: 1603677 (Python Code)

Max Activating Token Index: 690

Text #13

Max Range: 0.8346. Min Range: -0.8346

Max Act: 0.7347. Min Act: -0.0000

Data Index: 1360740 (Python Code)

Max Activating Token Index: 627

Text #14

Max Range: 0.8346. Min Range: -0.8346

Max Act: 0.7305. Min Act: 0.0000

Data Index: 1387793 (Python Code)

Max Activating Token Index: 10

Text #15

Max Range: 0.8346. Min Range: -0.8346

Max Act: 0.7287. Min Act: -0.0000

Data Index: 1452671 (Python Code)

Max Activating Token Index: 315

Text #16

Max Range: 0.8346. Min Range: -0.8346

Max Act: 0.6570. Min Act: -0.0000

Data Index: 1620368 (Python Code)

Max Activating Token Index: 862

Text #17

Max Range: 0.8346. Min Range: -0.8346

Max Act: 0.7139. Min Act: -0.0000

Data Index: 1373870 (Python Code)

Max Activating Token Index: 281

Text #18

Max Range: 0.8346. Min Range: -0.8346

Max Act: 0.6925. Min Act: -0.0000

Data Index: 1365372 (Python Code)

Max Activating Token Index: 850

Text #19

Max Range: 0.8346. Min Range: -0.8346

Max Act: 0.7199. Min Act: 0.0000

Data Index: 1635349 (Python Code)

Max Activating Token Index: 691