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

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

Neuron 3333 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.7955. Min Range: -2.7955

Max Act: 2.7955. Min Act: -0.0000

Data Index: 973646 (C4 (Web Text))

Max Activating Token Index: 864

Text #1

Max Range: 2.7955. Min Range: -2.7955

Max Act: 2.2599. Min Act: -0.0000

Data Index: 154645 (C4 (Web Text))

Max Activating Token Index: 834

Text #2

Max Range: 2.7955. Min Range: -2.7955

Max Act: 1.9678. Min Act: -0.0000

Data Index: 403191 (C4 (Web Text))

Max Activating Token Index: 980

Text #3

Max Range: 2.7955. Min Range: -2.7955

Max Act: 2.0768. Min Act: -0.0000

Data Index: 201649 (C4 (Web Text))

Max Activating Token Index: 634

Text #4

Max Range: 2.7955. Min Range: -2.7955

Max Act: 1.9221. Min Act: -0.0000

Data Index: 248776 (C4 (Web Text))

Max Activating Token Index: 942

Text #5

Max Range: 2.7955. Min Range: -2.7955

Max Act: 1.9915. Min Act: -0.0000

Data Index: 153227 (C4 (Web Text))

Max Activating Token Index: 886

Text #6

Max Range: 2.7955. Min Range: -2.7955

Max Act: 1.8914. Min Act: -0.0000

Data Index: 603313 (C4 (Web Text))

Max Activating Token Index: 428

Text #7

Max Range: 2.7955. Min Range: -2.7955

Max Act: 1.8776. Min Act: -0.0000

Data Index: 1045167 (C4 (Web Text))

Max Activating Token Index: 429

Text #8

Max Range: 2.7955. Min Range: -2.7955

Max Act: 1.8188. Min Act: -0.0000

Data Index: 1275722 (C4 (Web Text))

Max Activating Token Index: 270

Text #9

Max Range: 2.7955. Min Range: -2.7955

Max Act: 1.9297. Min Act: -0.0000

Data Index: 1201060 (C4 (Web Text))

Max Activating Token Index: 346

Text #10

Max Range: 2.7955. Min Range: -2.7955

Max Act: 1.8449. Min Act: -0.0000

Data Index: 1284334 (C4 (Web Text))

Max Activating Token Index: 371

Text #11

Max Range: 2.7955. Min Range: -2.7955

Max Act: 1.8156. Min Act: -0.0000

Data Index: 627091 (C4 (Web Text))

Max Activating Token Index: 526

Text #12

Max Range: 2.7955. Min Range: -2.7955

Max Act: 1.8200. Min Act: -0.0000

Data Index: 393882 (C4 (Web Text))

Max Activating Token Index: 674

Text #13

Max Range: 2.7955. Min Range: -2.7955

Max Act: 1.7052. Min Act: -0.0000

Data Index: 853749 (C4 (Web Text))

Max Activating Token Index: 987

Text #14

Max Range: 2.7955. Min Range: -2.7955

Max Act: 1.7744. Min Act: -0.0000

Data Index: 660651 (C4 (Web Text))

Max Activating Token Index: 896

Text #15

Max Range: 2.7955. Min Range: -2.7955

Max Act: 1.5547. Min Act: -0.0000

Data Index: 241510 (C4 (Web Text))

Max Activating Token Index: 201

Text #16

Max Range: 2.7955. Min Range: -2.7955

Max Act: 1.8570. Min Act: -0.0000

Data Index: 680872 (C4 (Web Text))

Max Activating Token Index: 937

Text #17

Max Range: 2.7955. Min Range: -2.7955

Max Act: 1.7422. Min Act: -0.0000

Data Index: 367926 (C4 (Web Text))

Max Activating Token Index: 430

Text #18

Max Range: 2.7955. Min Range: -2.7955

Max Act: 1.7064. Min Act: -0.0000

Data Index: 797489 (C4 (Web Text))

Max Activating Token Index: 828

Text #19

Max Range: 2.7955. Min Range: -2.7955

Max Act: 1.6100. Min Act: -0.0000

Data Index: 1336377 (C4 (Web Text))

Max Activating Token Index: 963