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

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

Neuron 1815 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5353. Min Range: -1.5353

Max Act: 1.5353. Min Act: 0.0001

Data Index: 1454126 (Python Code)

Max Activating Token Index: 465

Text #1

Max Range: 1.5353. Min Range: -1.5353

Max Act: 1.3523. Min Act: -0.0000

Data Index: 1580897 (Python Code)

Max Activating Token Index: 942

Text #2

Max Range: 1.5353. Min Range: -1.5353

Max Act: 1.3235. Min Act: 0.0000

Data Index: 1555789 (Python Code)

Max Activating Token Index: 284

Text #3

Max Range: 1.5353. Min Range: -1.5353

Max Act: 1.2502. Min Act: 0.0001

Data Index: 1491357 (Python Code)

Max Activating Token Index: 281

Text #4

Max Range: 1.5353. Min Range: -1.5353

Max Act: 1.2109. Min Act: 0.0001

Data Index: 1603489 (Python Code)

Max Activating Token Index: 38

Text #5

Max Range: 1.5353. Min Range: -1.5353

Max Act: 1.1926. Min Act: 0.0001

Data Index: 1461512 (Python Code)

Max Activating Token Index: 53

Text #6

Max Range: 1.5353. Min Range: -1.5353

Max Act: 1.0768. Min Act: 0.0001

Data Index: 1596381 (Python Code)

Max Activating Token Index: 184

Text #7

Max Range: 1.5353. Min Range: -1.5353

Max Act: 1.1538. Min Act: 0.0000

Data Index: 1441109 (Python Code)

Max Activating Token Index: 79

Text #8

Max Range: 1.5353. Min Range: -1.5353

Max Act: 1.1016. Min Act: 0.0001

Data Index: 1572658 (Python Code)

Max Activating Token Index: 816

Text #9

Max Range: 1.5353. Min Range: -1.5353

Max Act: 1.0860. Min Act: 0.0001

Data Index: 1526721 (Python Code)

Max Activating Token Index: 438

Text #10

Max Range: 1.5353. Min Range: -1.5353

Max Act: 1.0945. Min Act: 0.0001

Data Index: 1375444 (Python Code)

Max Activating Token Index: 159

Text #11

Max Range: 1.5353. Min Range: -1.5353

Max Act: 1.0937. Min Act: 0.0001

Data Index: 1634734 (Python Code)

Max Activating Token Index: 465

Text #12

Max Range: 1.5353. Min Range: -1.5353

Max Act: 1.0627. Min Act: -0.0000

Data Index: 1638825 (Python Code)

Max Activating Token Index: 343

Text #13

Max Range: 1.5353. Min Range: -1.5353

Max Act: 1.0720. Min Act: 0.0001

Data Index: 1401004 (Python Code)

Max Activating Token Index: 154

Text #14

Max Range: 1.5353. Min Range: -1.5353

Max Act: 1.0346. Min Act: -0.0000

Data Index: 1467343 (Python Code)

Max Activating Token Index: 128

Text #15

Max Range: 1.5353. Min Range: -1.5353

Max Act: 1.0214. Min Act: -0.0000

Data Index: 1591663 (Python Code)

Max Activating Token Index: 36

Text #16

Max Range: 1.5353. Min Range: -1.5353

Max Act: 0.9771. Min Act: 0.0001

Data Index: 1560133 (Python Code)

Max Activating Token Index: 125

Text #17

Max Range: 1.5353. Min Range: -1.5353

Max Act: 0.9766. Min Act: 0.0001

Data Index: 1579524 (Python Code)

Max Activating Token Index: 327

Text #18

Max Range: 1.5353. Min Range: -1.5353

Max Act: 0.9970. Min Act: 0.0000

Data Index: 1428364 (Python Code)

Max Activating Token Index: 499

Text #19

Max Range: 1.5353. Min Range: -1.5353

Max Act: 0.9924. Min Act: -0.0000

Data Index: 1413158 (Python Code)

Max Activating Token Index: 818