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

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

Neuron 3993 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.4663. Min Act: -0.0000

Data Index: 1530073 (Python Code)

Max Activating Token Index: 885

Text #1

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.3966. Min Act: -0.0000

Data Index: 1602137 (Python Code)

Max Activating Token Index: 974

Text #2

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.3880. Min Act: -0.0000

Data Index: 1429582 (Python Code)

Max Activating Token Index: 37

Text #3

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.3741. Min Act: -0.0001

Data Index: 1400895 (Python Code)

Max Activating Token Index: 5

Text #4

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.3677. Min Act: -0.0001

Data Index: 1519846 (Python Code)

Max Activating Token Index: 708

Text #5

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.3501. Min Act: -0.0001

Data Index: 1565926 (Python Code)

Max Activating Token Index: 203

Text #6

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.3441. Min Act: -0.0000

Data Index: 1623077 (Python Code)

Max Activating Token Index: 228

Text #7

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.3260. Min Act: -0.0000

Data Index: 1562904 (Python Code)

Max Activating Token Index: 476

Text #8

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.3400. Min Act: -0.0001

Data Index: 1503780 (Python Code)

Max Activating Token Index: 776

Text #9

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.3321. Min Act: -0.0001

Data Index: 1574087 (Python Code)

Max Activating Token Index: 88

Text #10

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.3209. Min Act: -0.0001

Data Index: 1601173 (Python Code)

Max Activating Token Index: 175

Text #11

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.3326. Min Act: -0.0001

Data Index: 1482546 (Python Code)

Max Activating Token Index: 942

Text #12

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.3313. Min Act: -0.0000

Data Index: 1388958 (Python Code)

Max Activating Token Index: 65

Text #13

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.3270. Min Act: -0.0001

Data Index: 1553423 (Python Code)

Max Activating Token Index: 179

Text #14

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.3127. Min Act: -0.0001

Data Index: 1543879 (Python Code)

Max Activating Token Index: 783

Text #15

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.3148. Min Act: -0.0001

Data Index: 1385931 (Python Code)

Max Activating Token Index: 735

Text #16

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.3224. Min Act: -0.0000

Data Index: 1525932 (Python Code)

Max Activating Token Index: 21

Text #17

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.3290. Min Act: -0.0001

Data Index: 1498607 (Python Code)

Max Activating Token Index: 79

Text #18

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.3178. Min Act: -0.0001

Data Index: 1582287 (Python Code)

Max Activating Token Index: 386

Text #19

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.3181. Min Act: -0.0001

Data Index: 1455132 (Python Code)

Max Activating Token Index: 16