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

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

Neuron 3893 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: 6.0981. Min Range: -6.0981

Max Act: 6.0981. Min Act: -0.0001

Data Index: 1646952 (Python Code)

Max Activating Token Index: 861

Text #1

Max Range: 6.0981. Min Range: -6.0981

Max Act: 5.5312. Min Act: -0.0001

Data Index: 1471101 (Python Code)

Max Activating Token Index: 760

Text #2

Max Range: 6.0981. Min Range: -6.0981

Max Act: 4.8992. Min Act: -0.0000

Data Index: 1446280 (Python Code)

Max Activating Token Index: 861

Text #3

Max Range: 6.0981. Min Range: -6.0981

Max Act: 4.7699. Min Act: -0.0000

Data Index: 1642393 (Python Code)

Max Activating Token Index: 757

Text #4

Max Range: 6.0981. Min Range: -6.0981

Max Act: 5.1550. Min Act: -0.0000

Data Index: 1405126 (Python Code)

Max Activating Token Index: 219

Text #5

Max Range: 6.0981. Min Range: -6.0981

Max Act: 4.4050. Min Act: -0.0001

Data Index: 1108748 (C4 (Web Text))

Max Activating Token Index: 18

Text #6

Max Range: 6.0981. Min Range: -6.0981

Max Act: 4.2983. Min Act: -0.0001

Data Index: 1560626 (Python Code)

Max Activating Token Index: 822

Text #7

Max Range: 6.0981. Min Range: -6.0981

Max Act: 4.1003. Min Act: -0.0000

Data Index: 1554346 (Python Code)

Max Activating Token Index: 829

Text #8

Max Range: 6.0981. Min Range: -6.0981

Max Act: 4.3394. Min Act: -0.0000

Data Index: 1496731 (Python Code)

Max Activating Token Index: 631

Text #9

Max Range: 6.0981. Min Range: -6.0981

Max Act: 3.8820. Min Act: -0.0000

Data Index: 1377054 (Python Code)

Max Activating Token Index: 454

Text #10

Max Range: 6.0981. Min Range: -6.0981

Max Act: 3.8347. Min Act: -0.0000

Data Index: 1607590 (Python Code)

Max Activating Token Index: 431

Text #11

Max Range: 6.0981. Min Range: -6.0981

Max Act: 4.2175. Min Act: -0.0000

Data Index: 1561193 (Python Code)

Max Activating Token Index: 512

Text #12

Max Range: 6.0981. Min Range: -6.0981

Max Act: 3.8198. Min Act: -0.0000

Data Index: 629931 (C4 (Web Text))

Max Activating Token Index: 63

Text #13

Max Range: 6.0981. Min Range: -6.0981

Max Act: 4.1677. Min Act: -0.0000

Data Index: 1408169 (Python Code)

Max Activating Token Index: 989

Text #14

Max Range: 6.0981. Min Range: -6.0981

Max Act: 3.7349. Min Act: -0.0000

Data Index: 1467797 (Python Code)

Max Activating Token Index: 560

Text #15

Max Range: 6.0981. Min Range: -6.0981

Max Act: 4.2470. Min Act: -0.0000

Data Index: 1417052 (Python Code)

Max Activating Token Index: 366

Text #16

Max Range: 6.0981. Min Range: -6.0981

Max Act: 3.8559. Min Act: -0.0001

Data Index: 478426 (C4 (Web Text))

Max Activating Token Index: 629

Text #17

Max Range: 6.0981. Min Range: -6.0981

Max Act: 3.7211. Min Act: -0.0001

Data Index: 1602908 (Python Code)

Max Activating Token Index: 317

Text #18

Max Range: 6.0981. Min Range: -6.0981

Max Act: 3.8565. Min Act: -0.0000

Data Index: 1566509 (Python Code)

Max Activating Token Index: 398

Text #19

Max Range: 6.0981. Min Range: -6.0981

Max Act: 3.5304. Min Act: -0.0001

Data Index: 1628972 (Python Code)

Max Activating Token Index: 254