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

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

Neuron 3383 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6635. Min Range: -0.6635

Max Act: 0.6635. Min Act: -0.0000

Data Index: 1028686 (C4 (Web Text))

Max Activating Token Index: 227

Text #1

Max Range: 0.6635. Min Range: -0.6635

Max Act: 0.5983. Min Act: -0.0000

Data Index: 1138722 (C4 (Web Text))

Max Activating Token Index: 43

Text #2

Max Range: 0.6635. Min Range: -0.6635

Max Act: 0.5759. Min Act: -0.0000

Data Index: 1291329 (C4 (Web Text))

Max Activating Token Index: 759

Text #3

Max Range: 0.6635. Min Range: -0.6635

Max Act: 0.5566. Min Act: -0.0000

Data Index: 20630 (C4 (Web Text))

Max Activating Token Index: 397

Text #4

Max Range: 0.6635. Min Range: -0.6635

Max Act: 0.5227. Min Act: -0.0000

Data Index: 59563 (C4 (Web Text))

Max Activating Token Index: 400

Text #5

Max Range: 0.6635. Min Range: -0.6635

Max Act: 0.4857. Min Act: -0.0000

Data Index: 151875 (C4 (Web Text))

Max Activating Token Index: 764

Text #6

Max Range: 0.6635. Min Range: -0.6635

Max Act: 0.4923. Min Act: -0.0000

Data Index: 189752 (C4 (Web Text))

Max Activating Token Index: 647

Text #7

Max Range: 0.6635. Min Range: -0.6635

Max Act: 0.3905. Min Act: -0.0000

Data Index: 754826 (C4 (Web Text))

Max Activating Token Index: 908

Text #8

Max Range: 0.6635. Min Range: -0.6635

Max Act: 0.4412. Min Act: -0.0000

Data Index: 778803 (C4 (Web Text))

Max Activating Token Index: 51

Text #9

Max Range: 0.6635. Min Range: -0.6635

Max Act: 0.4038. Min Act: -0.0000

Data Index: 1600405 (Python Code)

Max Activating Token Index: 982

Text #10

Max Range: 0.6635. Min Range: -0.6635

Max Act: 0.3634. Min Act: -0.0000

Data Index: 1226768 (C4 (Web Text))

Max Activating Token Index: 446

Text #11

Max Range: 0.6635. Min Range: -0.6635

Max Act: 0.4204. Min Act: -0.0000

Data Index: 928497 (C4 (Web Text))

Max Activating Token Index: 834

Text #12

Max Range: 0.6635. Min Range: -0.6635

Max Act: 0.3720. Min Act: -0.0000

Data Index: 1397936 (Python Code)

Max Activating Token Index: 1022

Text #13

Max Range: 0.6635. Min Range: -0.6635

Max Act: 0.3818. Min Act: -0.0000

Data Index: 1047552 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.6635. Min Range: -0.6635

Max Act: 0.3533. Min Act: -0.0000

Data Index: 1470988 (Python Code)

Max Activating Token Index: 889

Text #15

Max Range: 0.6635. Min Range: -0.6635

Max Act: 0.3629. Min Act: -0.0000

Data Index: 1608966 (Python Code)

Max Activating Token Index: 896

Text #16

Max Range: 0.6635. Min Range: -0.6635

Max Act: 0.3772. Min Act: -0.0000

Data Index: 1476405 (Python Code)

Max Activating Token Index: 504

Text #17

Max Range: 0.6635. Min Range: -0.6635

Max Act: 0.3811. Min Act: -0.0000

Data Index: 569921 (C4 (Web Text))

Max Activating Token Index: 814

Text #18

Max Range: 0.6635. Min Range: -0.6635

Max Act: 0.3277. Min Act: -0.0000

Data Index: 1406556 (Python Code)

Max Activating Token Index: 480

Text #19

Max Range: 0.6635. Min Range: -0.6635

Max Act: 0.3461. Min Act: -0.0000

Data Index: 1561911 (Python Code)

Max Activating Token Index: 251