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

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

Neuron 2870 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2372. Min Range: -2.2372

Max Act: 2.2372. Min Act: 0.0001

Data Index: 1608352 (Python Code)

Max Activating Token Index: 7

Text #1

Max Range: 2.2372. Min Range: -2.2372

Max Act: 1.8273. Min Act: -0.0000

Data Index: 1152963 (C4 (Web Text))

Max Activating Token Index: 59

Text #2

Max Range: 2.2372. Min Range: -2.2372

Max Act: 1.6218. Min Act: -0.0000

Data Index: 922820 (C4 (Web Text))

Max Activating Token Index: 720

Text #3

Max Range: 2.2372. Min Range: -2.2372

Max Act: 1.6126. Min Act: -0.0000

Data Index: 1505472 (Python Code)

Max Activating Token Index: 27

Text #4

Max Range: 2.2372. Min Range: -2.2372

Max Act: 1.5759. Min Act: -0.0000

Data Index: 1646047 (Python Code)

Max Activating Token Index: 14

Text #5

Max Range: 2.2372. Min Range: -2.2372

Max Act: 1.5459. Min Act: 0.0000

Data Index: 1635790 (Python Code)

Max Activating Token Index: 58

Text #6

Max Range: 2.2372. Min Range: -2.2372

Max Act: 1.4885. Min Act: 0.0000

Data Index: 1593816 (Python Code)

Max Activating Token Index: 188

Text #7

Max Range: 2.2372. Min Range: -2.2372

Max Act: 1.4941. Min Act: -0.0000

Data Index: 1599633 (Python Code)

Max Activating Token Index: 24

Text #8

Max Range: 2.2372. Min Range: -2.2372

Max Act: 1.4915. Min Act: 0.0000

Data Index: 1363974 (Python Code)

Max Activating Token Index: 38

Text #9

Max Range: 2.2372. Min Range: -2.2372

Max Act: 1.4845. Min Act: -0.0000

Data Index: 1561165 (Python Code)

Max Activating Token Index: 719

Text #10

Max Range: 2.2372. Min Range: -2.2372

Max Act: 1.4862. Min Act: 0.0001

Data Index: 1557652 (Python Code)

Max Activating Token Index: 26

Text #11

Max Range: 2.2372. Min Range: -2.2372

Max Act: 1.4844. Min Act: -0.0000

Data Index: 1583841 (Python Code)

Max Activating Token Index: 98

Text #12

Max Range: 2.2372. Min Range: -2.2372

Max Act: 1.4796. Min Act: -0.0000

Data Index: 1498703 (Python Code)

Max Activating Token Index: 77

Text #13

Max Range: 2.2372. Min Range: -2.2372

Max Act: 1.3756. Min Act: 0.0000

Data Index: 1509175 (Python Code)

Max Activating Token Index: 632

Text #14

Max Range: 2.2372. Min Range: -2.2372

Max Act: 1.4862. Min Act: -0.0000

Data Index: 333653 (C4 (Web Text))

Max Activating Token Index: 8

Text #15

Max Range: 2.2372. Min Range: -2.2372

Max Act: 1.4315. Min Act: -0.0000

Data Index: 1483004 (Python Code)

Max Activating Token Index: 68

Text #16

Max Range: 2.2372. Min Range: -2.2372

Max Act: 1.5148. Min Act: 0.0000

Data Index: 1363046 (Python Code)

Max Activating Token Index: 687

Text #17

Max Range: 2.2372. Min Range: -2.2372

Max Act: 1.3371. Min Act: -0.0000

Data Index: 1352870 (C4 (Web Text))

Max Activating Token Index: 38

Text #18

Max Range: 2.2372. Min Range: -2.2372

Max Act: 1.4070. Min Act: -0.0000

Data Index: 1391568 (Python Code)

Max Activating Token Index: 483

Text #19

Max Range: 2.2372. Min Range: -2.2372

Max Act: 1.4540. Min Act: 0.0001

Data Index: 1632381 (Python Code)

Max Activating Token Index: 16