Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4742 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 5.9496. Min Range: -5.9496

Max Act: 5.6346. Min Act: -0.0000

Data Index: 1456662 (Python Code)

Max Activating Token Index: 854

Text #1

Max Range: 5.9496. Min Range: -5.9496

Max Act: 5.7472. Min Act: -0.0000

Data Index: 1547425 (Python Code)

Max Activating Token Index: 977

Text #2

Max Range: 5.9496. Min Range: -5.9496

Max Act: 5.8277. Min Act: -0.0000

Data Index: 1651835 (Python Code)

Max Activating Token Index: 685

Text #3

Max Range: 5.9496. Min Range: -5.9496

Max Act: 5.9496. Min Act: -0.0000

Data Index: 1519047 (Python Code)

Max Activating Token Index: 979

Text #4

Max Range: 5.9496. Min Range: -5.9496

Max Act: 5.4259. Min Act: -0.0000

Data Index: 1404756 (Python Code)

Max Activating Token Index: 737

Text #5

Max Range: 5.9496. Min Range: -5.9496

Max Act: 4.7244. Min Act: -0.0000

Data Index: 1390110 (Python Code)

Max Activating Token Index: 832

Text #6

Max Range: 5.9496. Min Range: -5.9496

Max Act: 5.4248. Min Act: -0.0000

Data Index: 1580000 (Python Code)

Max Activating Token Index: 658

Text #7

Max Range: 5.9496. Min Range: -5.9496

Max Act: 5.6145. Min Act: -0.0000

Data Index: 1648647 (Python Code)

Max Activating Token Index: 561

Text #8

Max Range: 5.9496. Min Range: -5.9496

Max Act: 5.5712. Min Act: -0.0000

Data Index: 1384196 (Python Code)

Max Activating Token Index: 902

Text #9

Max Range: 5.9496. Min Range: -5.9496

Max Act: 5.3311. Min Act: -0.0000

Data Index: 1459295 (Python Code)

Max Activating Token Index: 384

Text #10

Max Range: 5.9496. Min Range: -5.9496

Max Act: 5.3034. Min Act: -0.0000

Data Index: 1622157 (Python Code)

Max Activating Token Index: 683

Text #11

Max Range: 5.9496. Min Range: -5.9496

Max Act: 5.3042. Min Act: -0.0000

Data Index: 1654938 (Python Code)

Max Activating Token Index: 1007

Text #12

Max Range: 5.9496. Min Range: -5.9496

Max Act: 5.4190. Min Act: -0.0000

Data Index: 1559418 (Python Code)

Max Activating Token Index: 572

Text #13

Max Range: 5.9496. Min Range: -5.9496

Max Act: 5.3881. Min Act: -0.0000

Data Index: 1512462 (Python Code)

Max Activating Token Index: 802

Text #14

Max Range: 5.9496. Min Range: -5.9496

Max Act: 5.4178. Min Act: -0.0000

Data Index: 1654962 (Python Code)

Max Activating Token Index: 823

Text #15

Max Range: 5.9496. Min Range: -5.9496

Max Act: 5.0645. Min Act: -0.0000

Data Index: 1530354 (Python Code)

Max Activating Token Index: 281

Text #16

Max Range: 5.9496. Min Range: -5.9496

Max Act: 5.1974. Min Act: -0.0000

Data Index: 1373118 (Python Code)

Max Activating Token Index: 277

Text #17

Max Range: 5.9496. Min Range: -5.9496

Max Act: 5.4861. Min Act: -0.0000

Data Index: 1462003 (Python Code)

Max Activating Token Index: 575

Text #18

Max Range: 5.9496. Min Range: -5.9496

Max Act: 5.3027. Min Act: -0.0000

Data Index: 1598269 (Python Code)

Max Activating Token Index: 842

Text #19

Max Range: 5.9496. Min Range: -5.9496

Max Act: 5.2777. Min Act: -0.0000

Data Index: 1463153 (Python Code)

Max Activating Token Index: 602