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

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

Neuron 729 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5001. Min Range: -3.5001

Max Act: 3.5001. Min Act: -0.0000

Data Index: 1469537 (Python Code)

Max Activating Token Index: 91

Text #1

Max Range: 3.5001. Min Range: -3.5001

Max Act: 2.9527. Min Act: 0.0000

Data Index: 982705 (C4 (Web Text))

Max Activating Token Index: 778

Text #2

Max Range: 3.5001. Min Range: -3.5001

Max Act: 2.3854. Min Act: -0.0000

Data Index: 1064778 (C4 (Web Text))

Max Activating Token Index: 492

Text #3

Max Range: 3.5001. Min Range: -3.5001

Max Act: 1.8707. Min Act: -0.0000

Data Index: 1517281 (Python Code)

Max Activating Token Index: 315

Text #4

Max Range: 3.5001. Min Range: -3.5001

Max Act: 1.7615. Min Act: -0.0000

Data Index: 49937 (C4 (Web Text))

Max Activating Token Index: 47

Text #5

Max Range: 3.5001. Min Range: -3.5001

Max Act: 1.7306. Min Act: 0.0000

Data Index: 1612563 (Python Code)

Max Activating Token Index: 299

Text #6

Max Range: 3.5001. Min Range: -3.5001

Max Act: 1.7240. Min Act: -0.0000

Data Index: 1470797 (Python Code)

Max Activating Token Index: 788

Text #7

Max Range: 3.5001. Min Range: -3.5001

Max Act: 1.6828. Min Act: -0.0000

Data Index: 308003 (C4 (Web Text))

Max Activating Token Index: 621

Text #8

Max Range: 3.5001. Min Range: -3.5001

Max Act: 1.5941. Min Act: -0.0000

Data Index: 1398119 (Python Code)

Max Activating Token Index: 53

Text #9

Max Range: 3.5001. Min Range: -3.5001

Max Act: 1.7335. Min Act: 0.0000

Data Index: 752511 (C4 (Web Text))

Max Activating Token Index: 658

Text #10

Max Range: 3.5001. Min Range: -3.5001

Max Act: 1.6367. Min Act: 0.0000

Data Index: 307713 (C4 (Web Text))

Max Activating Token Index: 61

Text #11

Max Range: 3.5001. Min Range: -3.5001

Max Act: 1.5655. Min Act: -0.0000

Data Index: 1611002 (Python Code)

Max Activating Token Index: 988

Text #12

Max Range: 3.5001. Min Range: -3.5001

Max Act: 1.5337. Min Act: -0.0000

Data Index: 1497443 (Python Code)

Max Activating Token Index: 862

Text #13

Max Range: 3.5001. Min Range: -3.5001

Max Act: 1.4202. Min Act: -0.0000

Data Index: 716285 (C4 (Web Text))

Max Activating Token Index: 854

Text #14

Max Range: 3.5001. Min Range: -3.5001

Max Act: 1.4032. Min Act: -0.0000

Data Index: 1009662 (C4 (Web Text))

Max Activating Token Index: 745

Text #15

Max Range: 3.5001. Min Range: -3.5001

Max Act: 1.5661. Min Act: -0.0000

Data Index: 465193 (C4 (Web Text))

Max Activating Token Index: 539

Text #16

Max Range: 3.5001. Min Range: -3.5001

Max Act: 1.4218. Min Act: 0.0000

Data Index: 1588590 (Python Code)

Max Activating Token Index: 960

Text #17

Max Range: 3.5001. Min Range: -3.5001

Max Act: 1.5020. Min Act: -0.0000

Data Index: 551398 (C4 (Web Text))

Max Activating Token Index: 537

Text #18

Max Range: 3.5001. Min Range: -3.5001

Max Act: 1.4779. Min Act: 0.0001

Data Index: 232601 (C4 (Web Text))

Max Activating Token Index: 478

Text #19

Max Range: 3.5001. Min Range: -3.5001

Max Act: 1.5605. Min Act: -0.0000

Data Index: 1386782 (Python Code)

Max Activating Token Index: 629