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

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

Neuron 4691 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6748. Min Range: -1.6748

Max Act: 1.6748. Min Act: -0.0000

Data Index: 1476188 (Python Code)

Max Activating Token Index: 379

Text #1

Max Range: 1.6748. Min Range: -1.6748

Max Act: 1.1006. Min Act: -0.0000

Data Index: 1603799 (Python Code)

Max Activating Token Index: 223

Text #2

Max Range: 1.6748. Min Range: -1.6748

Max Act: 1.1078. Min Act: -0.0000

Data Index: 1622085 (Python Code)

Max Activating Token Index: 419

Text #3

Max Range: 1.6748. Min Range: -1.6748

Max Act: 1.1455. Min Act: -0.0000

Data Index: 1552955 (Python Code)

Max Activating Token Index: 549

Text #4

Max Range: 1.6748. Min Range: -1.6748

Max Act: 1.0773. Min Act: -0.0000

Data Index: 1470960 (Python Code)

Max Activating Token Index: 69

Text #5

Max Range: 1.6748. Min Range: -1.6748

Max Act: 1.0324. Min Act: -0.0000

Data Index: 1486006 (Python Code)

Max Activating Token Index: 871

Text #6

Max Range: 1.6748. Min Range: -1.6748

Max Act: 0.9648. Min Act: -0.0000

Data Index: 1428674 (Python Code)

Max Activating Token Index: 221

Text #7

Max Range: 1.6748. Min Range: -1.6748

Max Act: 0.9997. Min Act: -0.0000

Data Index: 1551646 (Python Code)

Max Activating Token Index: 339

Text #8

Max Range: 1.6748. Min Range: -1.6748

Max Act: 0.9940. Min Act: -0.0000

Data Index: 1649924 (Python Code)

Max Activating Token Index: 791

Text #9

Max Range: 1.6748. Min Range: -1.6748

Max Act: 0.9417. Min Act: -0.0000

Data Index: 1464423 (Python Code)

Max Activating Token Index: 856

Text #10

Max Range: 1.6748. Min Range: -1.6748

Max Act: 0.9985. Min Act: -0.0000

Data Index: 1389072 (Python Code)

Max Activating Token Index: 716

Text #11

Max Range: 1.6748. Min Range: -1.6748

Max Act: 0.9555. Min Act: -0.0000

Data Index: 1486405 (Python Code)

Max Activating Token Index: 448

Text #12

Max Range: 1.6748. Min Range: -1.6748

Max Act: 0.9450. Min Act: -0.0000

Data Index: 1439800 (Python Code)

Max Activating Token Index: 40

Text #13

Max Range: 1.6748. Min Range: -1.6748

Max Act: 0.9142. Min Act: -0.0000

Data Index: 1446104 (Python Code)

Max Activating Token Index: 264

Text #14

Max Range: 1.6748. Min Range: -1.6748

Max Act: 0.8797. Min Act: -0.0000

Data Index: 1566346 (Python Code)

Max Activating Token Index: 133

Text #15

Max Range: 1.6748. Min Range: -1.6748

Max Act: 0.8977. Min Act: -0.0000

Data Index: 1604815 (Python Code)

Max Activating Token Index: 769

Text #16

Max Range: 1.6748. Min Range: -1.6748

Max Act: 0.8988. Min Act: -0.0000

Data Index: 1477951 (Python Code)

Max Activating Token Index: 1011

Text #17

Max Range: 1.6748. Min Range: -1.6748

Max Act: 0.8472. Min Act: -0.0000

Data Index: 1409102 (Python Code)

Max Activating Token Index: 715

Text #18

Max Range: 1.6748. Min Range: -1.6748

Max Act: 0.8596. Min Act: -0.0000

Data Index: 1549763 (Python Code)

Max Activating Token Index: 510

Text #19

Max Range: 1.6748. Min Range: -1.6748

Max Act: 0.8002. Min Act: -0.0000

Data Index: 1609113 (Python Code)

Max Activating Token Index: 226