Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3831 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.6559. Min Range: -0.6559

Max Act: 0.6559. Min Act: -0.0000

Data Index: 1379799 (Python Code)

Max Activating Token Index: 69

Text #1

Max Range: 0.6559. Min Range: -0.6559

Max Act: 0.4338. Min Act: -0.0000

Data Index: 1376742 (Python Code)

Max Activating Token Index: 341

Text #2

Max Range: 0.6559. Min Range: -0.6559

Max Act: 0.3706. Min Act: -0.0000

Data Index: 1579464 (Python Code)

Max Activating Token Index: 568

Text #3

Max Range: 0.6559. Min Range: -0.6559

Max Act: 0.3538. Min Act: -0.0000

Data Index: 1615554 (Python Code)

Max Activating Token Index: 190

Text #4

Max Range: 0.6559. Min Range: -0.6559

Max Act: 0.3207. Min Act: -0.0000

Data Index: 1615355 (Python Code)

Max Activating Token Index: 741

Text #5

Max Range: 0.6559. Min Range: -0.6559

Max Act: 0.3402. Min Act: -0.0000

Data Index: 1563965 (Python Code)

Max Activating Token Index: 157

Text #6

Max Range: 0.6559. Min Range: -0.6559

Max Act: 0.3399. Min Act: -0.0000

Data Index: 1582533 (Python Code)

Max Activating Token Index: 664

Text #7

Max Range: 0.6559. Min Range: -0.6559

Max Act: 0.3492. Min Act: -0.0000

Data Index: 1552254 (Python Code)

Max Activating Token Index: 382

Text #8

Max Range: 0.6559. Min Range: -0.6559

Max Act: 0.3503. Min Act: -0.0000

Data Index: 1493299 (Python Code)

Max Activating Token Index: 569

Text #9

Max Range: 0.6559. Min Range: -0.6559

Max Act: 0.3371. Min Act: -0.0000

Data Index: 1435807 (Python Code)

Max Activating Token Index: 608

Text #10

Max Range: 0.6559. Min Range: -0.6559

Max Act: 0.3396. Min Act: -0.0000

Data Index: 1416449 (Python Code)

Max Activating Token Index: 342

Text #11

Max Range: 0.6559. Min Range: -0.6559

Max Act: 0.3369. Min Act: -0.0000

Data Index: 1636075 (Python Code)

Max Activating Token Index: 748

Text #12

Max Range: 0.6559. Min Range: -0.6559

Max Act: 0.3350. Min Act: -0.0000

Data Index: 1487895 (Python Code)

Max Activating Token Index: 339

Text #13

Max Range: 0.6559. Min Range: -0.6559

Max Act: 0.3322. Min Act: -0.0000

Data Index: 1575790 (Python Code)

Max Activating Token Index: 943

Text #14

Max Range: 0.6559. Min Range: -0.6559

Max Act: 0.3398. Min Act: -0.0000

Data Index: 1494593 (Python Code)

Max Activating Token Index: 849

Text #15

Max Range: 0.6559. Min Range: -0.6559

Max Act: 0.3095. Min Act: -0.0000

Data Index: 1422150 (Python Code)

Max Activating Token Index: 822

Text #16

Max Range: 0.6559. Min Range: -0.6559

Max Act: 0.3105. Min Act: -0.0000

Data Index: 1552804 (Python Code)

Max Activating Token Index: 495

Text #17

Max Range: 0.6559. Min Range: -0.6559

Max Act: 0.3320. Min Act: -0.0000

Data Index: 1437217 (Python Code)

Max Activating Token Index: 98

Text #18

Max Range: 0.6559. Min Range: -0.6559

Max Act: 0.3021. Min Act: -0.0000

Data Index: 1623342 (Python Code)

Max Activating Token Index: 854

Text #19

Max Range: 0.6559. Min Range: -0.6559

Max Act: 0.3097. Min Act: -0.0000

Data Index: 1379975 (Python Code)

Max Activating Token Index: 999