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

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

Neuron 278 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: 6.3880. Min Range: -6.3880

Max Act: 6.3880. Min Act: -0.0000

Data Index: 461335 (C4 (Web Text))

Max Activating Token Index: 48

Text #1

Max Range: 6.3880. Min Range: -6.3880

Max Act: 5.6858. Min Act: -0.0000

Data Index: 809444 (C4 (Web Text))

Max Activating Token Index: 463

Text #2

Max Range: 6.3880. Min Range: -6.3880

Max Act: 5.6335. Min Act: -0.0000

Data Index: 205840 (C4 (Web Text))

Max Activating Token Index: 271

Text #3

Max Range: 6.3880. Min Range: -6.3880

Max Act: 5.2780. Min Act: -0.0000

Data Index: 1138384 (C4 (Web Text))

Max Activating Token Index: 483

Text #4

Max Range: 6.3880. Min Range: -6.3880

Max Act: 5.3577. Min Act: -0.0000

Data Index: 632466 (C4 (Web Text))

Max Activating Token Index: 962

Text #5

Max Range: 6.3880. Min Range: -6.3880

Max Act: 4.9815. Min Act: -0.0000

Data Index: 1184489 (C4 (Web Text))

Max Activating Token Index: 776

Text #6

Max Range: 6.3880. Min Range: -6.3880

Max Act: 4.7732. Min Act: -0.0000

Data Index: 64917 (C4 (Web Text))

Max Activating Token Index: 62

Text #7

Max Range: 6.3880. Min Range: -6.3880

Max Act: 4.8549. Min Act: -0.0000

Data Index: 1140064 (C4 (Web Text))

Max Activating Token Index: 125

Text #8

Max Range: 6.3880. Min Range: -6.3880

Max Act: 5.1758. Min Act: -0.0000

Data Index: 100950 (C4 (Web Text))

Max Activating Token Index: 281

Text #9

Max Range: 6.3880. Min Range: -6.3880

Max Act: 4.9646. Min Act: -0.0000

Data Index: 466451 (C4 (Web Text))

Max Activating Token Index: 43

Text #10

Max Range: 6.3880. Min Range: -6.3880

Max Act: 5.3024. Min Act: -0.0000

Data Index: 1339253 (C4 (Web Text))

Max Activating Token Index: 541

Text #11

Max Range: 6.3880. Min Range: -6.3880

Max Act: 4.9620. Min Act: -0.0000

Data Index: 993621 (C4 (Web Text))

Max Activating Token Index: 1007

Text #12

Max Range: 6.3880. Min Range: -6.3880

Max Act: 4.9193. Min Act: -0.0000

Data Index: 1200332 (C4 (Web Text))

Max Activating Token Index: 904

Text #13

Max Range: 6.3880. Min Range: -6.3880

Max Act: 5.0269. Min Act: -0.0000

Data Index: 1138003 (C4 (Web Text))

Max Activating Token Index: 618

Text #14

Max Range: 6.3880. Min Range: -6.3880

Max Act: 5.3596. Min Act: -0.0000

Data Index: 489011 (C4 (Web Text))

Max Activating Token Index: 93

Text #15

Max Range: 6.3880. Min Range: -6.3880

Max Act: 4.8363. Min Act: -0.0000

Data Index: 1339749 (C4 (Web Text))

Max Activating Token Index: 415

Text #16

Max Range: 6.3880. Min Range: -6.3880

Max Act: 4.6397. Min Act: -0.0000

Data Index: 837516 (C4 (Web Text))

Max Activating Token Index: 523

Text #17

Max Range: 6.3880. Min Range: -6.3880

Max Act: 4.7973. Min Act: -0.0000

Data Index: 574046 (C4 (Web Text))

Max Activating Token Index: 206

Text #18

Max Range: 6.3880. Min Range: -6.3880

Max Act: 5.1546. Min Act: -0.0000

Data Index: 540217 (C4 (Web Text))

Max Activating Token Index: 925

Text #19

Max Range: 6.3880. Min Range: -6.3880

Max Act: 4.9736. Min Act: -0.0000

Data Index: 504777 (C4 (Web Text))

Max Activating Token Index: 793