Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3232 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5092. Min Range: -0.5092

Max Act: 0.5092. Min Act: -0.0001

Data Index: 1623245 (Python Code)

Max Activating Token Index: 105

Text #1

Max Range: 0.5092. Min Range: -0.5092

Max Act: 0.4691. Min Act: -0.0001

Data Index: 1647570 (Python Code)

Max Activating Token Index: 498

Text #2

Max Range: 0.5092. Min Range: -0.5092

Max Act: 0.4849. Min Act: -0.0001

Data Index: 1524946 (Python Code)

Max Activating Token Index: 58

Text #3

Max Range: 0.5092. Min Range: -0.5092

Max Act: 0.4474. Min Act: -0.0001

Data Index: 1588290 (Python Code)

Max Activating Token Index: 865

Text #4

Max Range: 0.5092. Min Range: -0.5092

Max Act: 0.4909. Min Act: -0.0001

Data Index: 1555384 (Python Code)

Max Activating Token Index: 54

Text #5

Max Range: 0.5092. Min Range: -0.5092

Max Act: 0.4518. Min Act: -0.0001

Data Index: 1421041 (Python Code)

Max Activating Token Index: 168

Text #6

Max Range: 0.5092. Min Range: -0.5092

Max Act: 0.4778. Min Act: -0.0001

Data Index: 1629763 (Python Code)

Max Activating Token Index: 500

Text #7

Max Range: 0.5092. Min Range: -0.5092

Max Act: 0.4469. Min Act: -0.0001

Data Index: 1444700 (Python Code)

Max Activating Token Index: 891

Text #8

Max Range: 0.5092. Min Range: -0.5092

Max Act: 0.4295. Min Act: -0.0001

Data Index: 1402329 (Python Code)

Max Activating Token Index: 6

Text #9

Max Range: 0.5092. Min Range: -0.5092

Max Act: 0.4400. Min Act: -0.0001

Data Index: 1431911 (Python Code)

Max Activating Token Index: 786

Text #10

Max Range: 0.5092. Min Range: -0.5092

Max Act: 0.4383. Min Act: -0.0001

Data Index: 1457964 (Python Code)

Max Activating Token Index: 223

Text #11

Max Range: 0.5092. Min Range: -0.5092

Max Act: 0.4355. Min Act: -0.0001

Data Index: 1542896 (Python Code)

Max Activating Token Index: 189

Text #12

Max Range: 0.5092. Min Range: -0.5092

Max Act: 0.4510. Min Act: -0.0001

Data Index: 1620518 (Python Code)

Max Activating Token Index: 244

Text #13

Max Range: 0.5092. Min Range: -0.5092

Max Act: 0.4494. Min Act: -0.0001

Data Index: 1578370 (Python Code)

Max Activating Token Index: 5

Text #14

Max Range: 0.5092. Min Range: -0.5092

Max Act: 0.4540. Min Act: -0.0001

Data Index: 1623697 (Python Code)

Max Activating Token Index: 580

Text #15

Max Range: 0.5092. Min Range: -0.5092

Max Act: 0.4061. Min Act: -0.0001

Data Index: 1475310 (Python Code)

Max Activating Token Index: 337

Text #16

Max Range: 0.5092. Min Range: -0.5092

Max Act: 0.4400. Min Act: -0.0001

Data Index: 1533034 (Python Code)

Max Activating Token Index: 553

Text #17

Max Range: 0.5092. Min Range: -0.5092

Max Act: 0.4490. Min Act: -0.0001

Data Index: 1522613 (Python Code)

Max Activating Token Index: 789

Text #18

Max Range: 0.5092. Min Range: -0.5092

Max Act: 0.4282. Min Act: -0.0001

Data Index: 1430737 (Python Code)

Max Activating Token Index: 66

Text #19

Max Range: 0.5092. Min Range: -0.5092

Max Act: 0.4104. Min Act: -0.0001

Data Index: 1560655 (Python Code)

Max Activating Token Index: 27