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

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

Neuron 3750 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: 1.8107. Min Range: -1.8107

Max Act: 1.8107. Min Act: -0.0000

Data Index: 1410529 (Python Code)

Max Activating Token Index: 364

Text #1

Max Range: 1.8107. Min Range: -1.8107

Max Act: 1.5888. Min Act: -0.0000

Data Index: 1374128 (Python Code)

Max Activating Token Index: 1021

Text #2

Max Range: 1.8107. Min Range: -1.8107

Max Act: 1.1593. Min Act: -0.0000

Data Index: 1421724 (Python Code)

Max Activating Token Index: 932

Text #3

Max Range: 1.8107. Min Range: -1.8107

Max Act: 1.2629. Min Act: -0.0000

Data Index: 1545662 (Python Code)

Max Activating Token Index: 147

Text #4

Max Range: 1.8107. Min Range: -1.8107

Max Act: 1.1639. Min Act: -0.0000

Data Index: 1491493 (Python Code)

Max Activating Token Index: 887

Text #5

Max Range: 1.8107. Min Range: -1.8107

Max Act: 1.1209. Min Act: -0.0000

Data Index: 1611950 (Python Code)

Max Activating Token Index: 643

Text #6

Max Range: 1.8107. Min Range: -1.8107

Max Act: 1.1306. Min Act: -0.0000

Data Index: 1560311 (Python Code)

Max Activating Token Index: 342

Text #7

Max Range: 1.8107. Min Range: -1.8107

Max Act: 0.9921. Min Act: -0.0000

Data Index: 1363782 (Python Code)

Max Activating Token Index: 995

Text #8

Max Range: 1.8107. Min Range: -1.8107

Max Act: 0.9571. Min Act: -0.0000

Data Index: 1512804 (Python Code)

Max Activating Token Index: 928

Text #9

Max Range: 1.8107. Min Range: -1.8107

Max Act: 0.8376. Min Act: -0.0000

Data Index: 1411618 (Python Code)

Max Activating Token Index: 258

Text #10

Max Range: 1.8107. Min Range: -1.8107

Max Act: 0.8020. Min Act: -0.0000

Data Index: 1438994 (Python Code)

Max Activating Token Index: 769

Text #11

Max Range: 1.8107. Min Range: -1.8107

Max Act: 0.7991. Min Act: -0.0000

Data Index: 1415115 (Python Code)

Max Activating Token Index: 678

Text #12

Max Range: 1.8107. Min Range: -1.8107

Max Act: 0.8058. Min Act: -0.0000

Data Index: 1562379 (Python Code)

Max Activating Token Index: 933

Text #13

Max Range: 1.8107. Min Range: -1.8107

Max Act: 0.7876. Min Act: -0.0000

Data Index: 1526523 (Python Code)

Max Activating Token Index: 315

Text #14

Max Range: 1.8107. Min Range: -1.8107

Max Act: 0.7173. Min Act: -0.0000

Data Index: 1649997 (Python Code)

Max Activating Token Index: 888

Text #15

Max Range: 1.8107. Min Range: -1.8107

Max Act: 0.7816. Min Act: -0.0000

Data Index: 1551173 (Python Code)

Max Activating Token Index: 624

Text #16

Max Range: 1.8107. Min Range: -1.8107

Max Act: 0.7281. Min Act: -0.0000

Data Index: 1625625 (Python Code)

Max Activating Token Index: 684

Text #17

Max Range: 1.8107. Min Range: -1.8107

Max Act: 0.7009. Min Act: -0.0000

Data Index: 1398030 (Python Code)

Max Activating Token Index: 581

Text #18

Max Range: 1.8107. Min Range: -1.8107

Max Act: 0.6854. Min Act: -0.0000

Data Index: 1536376 (Python Code)

Max Activating Token Index: 163

Text #19

Max Range: 1.8107. Min Range: -1.8107

Max Act: 0.7637. Min Act: -0.0000

Data Index: 1571270 (Python Code)

Max Activating Token Index: 714