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

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

Neuron 2891 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3699. Min Range: -0.3699

Max Act: 0.3699. Min Act: -0.0002

Data Index: 1521571 (Python Code)

Max Activating Token Index: 82

Text #1

Max Range: 0.3699. Min Range: -0.3699

Max Act: 0.3404. Min Act: -0.0002

Data Index: 1406242 (Python Code)

Max Activating Token Index: 54

Text #2

Max Range: 0.3699. Min Range: -0.3699

Max Act: 0.3150. Min Act: -0.0002

Data Index: 1515764 (Python Code)

Max Activating Token Index: 106

Text #3

Max Range: 0.3699. Min Range: -0.3699

Max Act: 0.3078. Min Act: -0.0002

Data Index: 1580606 (Python Code)

Max Activating Token Index: 103

Text #4

Max Range: 0.3699. Min Range: -0.3699

Max Act: 0.3134. Min Act: -0.0002

Data Index: 1631856 (Python Code)

Max Activating Token Index: 55

Text #5

Max Range: 0.3699. Min Range: -0.3699

Max Act: 0.2919. Min Act: -0.0002

Data Index: 1401604 (Python Code)

Max Activating Token Index: 152

Text #6

Max Range: 0.3699. Min Range: -0.3699

Max Act: 0.2751. Min Act: -0.0002

Data Index: 1496769 (Python Code)

Max Activating Token Index: 212

Text #7

Max Range: 0.3699. Min Range: -0.3699

Max Act: 0.2706. Min Act: -0.0002

Data Index: 1506053 (Python Code)

Max Activating Token Index: 1018

Text #8

Max Range: 0.3699. Min Range: -0.3699

Max Act: 0.2678. Min Act: -0.0002

Data Index: 1526629 (Python Code)

Max Activating Token Index: 310

Text #9

Max Range: 0.3699. Min Range: -0.3699

Max Act: 0.2653. Min Act: -0.0002

Data Index: 1450275 (Python Code)

Max Activating Token Index: 699

Text #10

Max Range: 0.3699. Min Range: -0.3699

Max Act: 0.2658. Min Act: -0.0002

Data Index: 1510743 (Python Code)

Max Activating Token Index: 393

Text #11

Max Range: 0.3699. Min Range: -0.3699

Max Act: 0.2580. Min Act: -0.0002

Data Index: 1381393 (Python Code)

Max Activating Token Index: 894

Text #12

Max Range: 0.3699. Min Range: -0.3699

Max Act: 0.2490. Min Act: -0.0002

Data Index: 1434512 (Python Code)

Max Activating Token Index: 200

Text #13

Max Range: 0.3699. Min Range: -0.3699

Max Act: 0.2553. Min Act: -0.0002

Data Index: 1464450 (Python Code)

Max Activating Token Index: 492

Text #14

Max Range: 0.3699. Min Range: -0.3699

Max Act: 0.2457. Min Act: -0.0002

Data Index: 1383044 (Python Code)

Max Activating Token Index: 694

Text #15

Max Range: 0.3699. Min Range: -0.3699

Max Act: 0.2497. Min Act: -0.0002

Data Index: 1642498 (Python Code)

Max Activating Token Index: 365

Text #16

Max Range: 0.3699. Min Range: -0.3699

Max Act: 0.2363. Min Act: -0.0002

Data Index: 1419281 (Python Code)

Max Activating Token Index: 306

Text #17

Max Range: 0.3699. Min Range: -0.3699

Max Act: 0.2314. Min Act: -0.0002

Data Index: 1592051 (Python Code)

Max Activating Token Index: 172

Text #18

Max Range: 0.3699. Min Range: -0.3699

Max Act: 0.2179. Min Act: -0.0002

Data Index: 1511762 (Python Code)

Max Activating Token Index: 162

Text #19

Max Range: 0.3699. Min Range: -0.3699

Max Act: 0.2080. Min Act: -0.0002

Data Index: 1371182 (Python Code)

Max Activating Token Index: 13