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

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

Neuron 2928 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: 3.0811. Min Range: -3.0811

Max Act: 3.0811. Min Act: -0.0000

Data Index: 1567312 (Python Code)

Max Activating Token Index: 262

Text #1

Max Range: 3.0811. Min Range: -3.0811

Max Act: 2.8751. Min Act: -0.0000

Data Index: 1630582 (Python Code)

Max Activating Token Index: 517

Text #2

Max Range: 3.0811. Min Range: -3.0811

Max Act: 2.8121. Min Act: -0.0000

Data Index: 1478352 (Python Code)

Max Activating Token Index: 713

Text #3

Max Range: 3.0811. Min Range: -3.0811

Max Act: 2.9295. Min Act: -0.0000

Data Index: 1510348 (Python Code)

Max Activating Token Index: 303

Text #4

Max Range: 3.0811. Min Range: -3.0811

Max Act: 2.7459. Min Act: -0.0000

Data Index: 1515206 (Python Code)

Max Activating Token Index: 960

Text #5

Max Range: 3.0811. Min Range: -3.0811

Max Act: 2.6982. Min Act: -0.0000

Data Index: 1513958 (Python Code)

Max Activating Token Index: 172

Text #6

Max Range: 3.0811. Min Range: -3.0811

Max Act: 2.4633. Min Act: -0.0000

Data Index: 610661 (C4 (Web Text))

Max Activating Token Index: 276

Text #7

Max Range: 3.0811. Min Range: -3.0811

Max Act: 2.5650. Min Act: -0.0000

Data Index: 1509298 (Python Code)

Max Activating Token Index: 195

Text #8

Max Range: 3.0811. Min Range: -3.0811

Max Act: 2.3557. Min Act: -0.0000

Data Index: 1565837 (Python Code)

Max Activating Token Index: 776

Text #9

Max Range: 3.0811. Min Range: -3.0811

Max Act: 2.4612. Min Act: -0.0000

Data Index: 1407561 (Python Code)

Max Activating Token Index: 433

Text #10

Max Range: 3.0811. Min Range: -3.0811

Max Act: 2.4515. Min Act: -0.0000

Data Index: 1589060 (Python Code)

Max Activating Token Index: 251

Text #11

Max Range: 3.0811. Min Range: -3.0811

Max Act: 2.3619. Min Act: -0.0000

Data Index: 1377346 (Python Code)

Max Activating Token Index: 448

Text #12

Max Range: 3.0811. Min Range: -3.0811

Max Act: 2.2396. Min Act: -0.0000

Data Index: 1638656 (Python Code)

Max Activating Token Index: 814

Text #13

Max Range: 3.0811. Min Range: -3.0811

Max Act: 2.4394. Min Act: -0.0000

Data Index: 1422529 (Python Code)

Max Activating Token Index: 866

Text #14

Max Range: 3.0811. Min Range: -3.0811

Max Act: 2.1882. Min Act: -0.0000

Data Index: 1613036 (Python Code)

Max Activating Token Index: 781

Text #15

Max Range: 3.0811. Min Range: -3.0811

Max Act: 2.2823. Min Act: -0.0000

Data Index: 1632251 (Python Code)

Max Activating Token Index: 903

Text #16

Max Range: 3.0811. Min Range: -3.0811

Max Act: 2.1038. Min Act: -0.0000

Data Index: 1536298 (Python Code)

Max Activating Token Index: 325

Text #17

Max Range: 3.0811. Min Range: -3.0811

Max Act: 2.1213. Min Act: -0.0000

Data Index: 1560354 (Python Code)

Max Activating Token Index: 978

Text #18

Max Range: 3.0811. Min Range: -3.0811

Max Act: 2.3314. Min Act: -0.0000

Data Index: 1539349 (Python Code)

Max Activating Token Index: 537

Text #19

Max Range: 3.0811. Min Range: -3.0811

Max Act: 2.1953. Min Act: -0.0000

Data Index: 1406942 (Python Code)

Max Activating Token Index: 817