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

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

Neuron 3579 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3691. Min Range: -0.3691

Max Act: 0.3307. Min Act: 0.0000

Data Index: 1208685 (C4 (Web Text))

Max Activating Token Index: 854

Text #1

Max Range: 0.3691. Min Range: -0.3691

Max Act: 0.3360. Min Act: -0.0000

Data Index: 1024422 (C4 (Web Text))

Max Activating Token Index: 961

Text #2

Max Range: 0.3691. Min Range: -0.3691

Max Act: 0.3691. Min Act: -0.0000

Data Index: 1532717 (Python Code)

Max Activating Token Index: 753

Text #3

Max Range: 0.3691. Min Range: -0.3691

Max Act: 0.3449. Min Act: -0.0000

Data Index: 281802 (C4 (Web Text))

Max Activating Token Index: 984

Text #4

Max Range: 0.3691. Min Range: -0.3691

Max Act: 0.3334. Min Act: -0.0000

Data Index: 1375077 (Python Code)

Max Activating Token Index: 311

Text #5

Max Range: 0.3691. Min Range: -0.3691

Max Act: 0.3194. Min Act: -0.0000

Data Index: 1304932 (C4 (Web Text))

Max Activating Token Index: 294

Text #6

Max Range: 0.3691. Min Range: -0.3691

Max Act: 0.3193. Min Act: -0.0000

Data Index: 1019076 (C4 (Web Text))

Max Activating Token Index: 58

Text #7

Max Range: 0.3691. Min Range: -0.3691

Max Act: 0.3170. Min Act: 0.0000

Data Index: 281124 (C4 (Web Text))

Max Activating Token Index: 12

Text #8

Max Range: 0.3691. Min Range: -0.3691

Max Act: 0.2957. Min Act: -0.0000

Data Index: 1411567 (Python Code)

Max Activating Token Index: 366

Text #9

Max Range: 0.3691. Min Range: -0.3691

Max Act: 0.3073. Min Act: -0.0000

Data Index: 1652574 (Python Code)

Max Activating Token Index: 486

Text #10

Max Range: 0.3691. Min Range: -0.3691

Max Act: 0.2962. Min Act: -0.0000

Data Index: 1096741 (C4 (Web Text))

Max Activating Token Index: 466

Text #11

Max Range: 0.3691. Min Range: -0.3691

Max Act: 0.2919. Min Act: -0.0000

Data Index: 705982 (C4 (Web Text))

Max Activating Token Index: 55

Text #12

Max Range: 0.3691. Min Range: -0.3691

Max Act: 0.2900. Min Act: -0.0000

Data Index: 1435568 (Python Code)

Max Activating Token Index: 475

Text #13

Max Range: 0.3691. Min Range: -0.3691

Max Act: 0.2797. Min Act: -0.0000

Data Index: 1406461 (Python Code)

Max Activating Token Index: 152

Text #14

Max Range: 0.3691. Min Range: -0.3691

Max Act: 0.3084. Min Act: -0.0000

Data Index: 943748 (C4 (Web Text))

Max Activating Token Index: 228

Text #15

Max Range: 0.3691. Min Range: -0.3691

Max Act: 0.2757. Min Act: -0.0000

Data Index: 1524762 (Python Code)

Max Activating Token Index: 330

Text #16

Max Range: 0.3691. Min Range: -0.3691

Max Act: 0.2773. Min Act: -0.0000

Data Index: 691706 (C4 (Web Text))

Max Activating Token Index: 639

Text #17

Max Range: 0.3691. Min Range: -0.3691

Max Act: 0.2931. Min Act: -0.0000

Data Index: 1552554 (Python Code)

Max Activating Token Index: 920

Text #18

Max Range: 0.3691. Min Range: -0.3691

Max Act: 0.2815. Min Act: -0.0000

Data Index: 1632586 (Python Code)

Max Activating Token Index: 491

Text #19

Max Range: 0.3691. Min Range: -0.3691

Max Act: 0.2718. Min Act: -0.0000

Data Index: 47626 (C4 (Web Text))

Max Activating Token Index: 669