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

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

Neuron 1639 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: 0.3655. Min Range: -0.3655

Max Act: 0.3655. Min Act: -0.0000

Data Index: 816793 (C4 (Web Text))

Max Activating Token Index: 942

Text #1

Max Range: 0.3655. Min Range: -0.3655

Max Act: 0.3138. Min Act: -0.0000

Data Index: 84672 (C4 (Web Text))

Max Activating Token Index: 138

Text #2

Max Range: 0.3655. Min Range: -0.3655

Max Act: 0.3298. Min Act: -0.0000

Data Index: 1182298 (C4 (Web Text))

Max Activating Token Index: 870

Text #3

Max Range: 0.3655. Min Range: -0.3655

Max Act: 0.3134. Min Act: -0.0000

Data Index: 185218 (C4 (Web Text))

Max Activating Token Index: 625

Text #4

Max Range: 0.3655. Min Range: -0.3655

Max Act: 0.3016. Min Act: -0.0000

Data Index: 204038 (C4 (Web Text))

Max Activating Token Index: 943

Text #5

Max Range: 0.3655. Min Range: -0.3655

Max Act: 0.2994. Min Act: -0.0000

Data Index: 192812 (C4 (Web Text))

Max Activating Token Index: 90

Text #6

Max Range: 0.3655. Min Range: -0.3655

Max Act: 0.2990. Min Act: -0.0000

Data Index: 1090782 (C4 (Web Text))

Max Activating Token Index: 787

Text #7

Max Range: 0.3655. Min Range: -0.3655

Max Act: 0.3016. Min Act: -0.0000

Data Index: 257046 (C4 (Web Text))

Max Activating Token Index: 314

Text #8

Max Range: 0.3655. Min Range: -0.3655

Max Act: 0.2821. Min Act: -0.0000

Data Index: 1161651 (C4 (Web Text))

Max Activating Token Index: 992

Text #9

Max Range: 0.3655. Min Range: -0.3655

Max Act: 0.3021. Min Act: -0.0000

Data Index: 715980 (C4 (Web Text))

Max Activating Token Index: 414

Text #10

Max Range: 0.3655. Min Range: -0.3655

Max Act: 0.2683. Min Act: -0.0000

Data Index: 345885 (C4 (Web Text))

Max Activating Token Index: 878

Text #11

Max Range: 0.3655. Min Range: -0.3655

Max Act: 0.2580. Min Act: -0.0000

Data Index: 595144 (C4 (Web Text))

Max Activating Token Index: 749

Text #12

Max Range: 0.3655. Min Range: -0.3655

Max Act: 0.2609. Min Act: -0.0000

Data Index: 75886 (C4 (Web Text))

Max Activating Token Index: 360

Text #13

Max Range: 0.3655. Min Range: -0.3655

Max Act: 0.2585. Min Act: -0.0000

Data Index: 53303 (C4 (Web Text))

Max Activating Token Index: 157

Text #14

Max Range: 0.3655. Min Range: -0.3655

Max Act: 0.2429. Min Act: -0.0000

Data Index: 1253305 (C4 (Web Text))

Max Activating Token Index: 488

Text #15

Max Range: 0.3655. Min Range: -0.3655

Max Act: 0.2472. Min Act: -0.0000

Data Index: 572630 (C4 (Web Text))

Max Activating Token Index: 28

Text #16

Max Range: 0.3655. Min Range: -0.3655

Max Act: 0.2388. Min Act: -0.0000

Data Index: 1011362 (C4 (Web Text))

Max Activating Token Index: 462

Text #17

Max Range: 0.3655. Min Range: -0.3655

Max Act: 0.2470. Min Act: -0.0000

Data Index: 1071886 (C4 (Web Text))

Max Activating Token Index: 47

Text #18

Max Range: 0.3655. Min Range: -0.3655

Max Act: 0.2341. Min Act: -0.0000

Data Index: 378771 (C4 (Web Text))

Max Activating Token Index: 43

Text #19

Max Range: 0.3655. Min Range: -0.3655

Max Act: 0.2329. Min Act: -0.0000

Data Index: 447985 (C4 (Web Text))

Max Activating Token Index: 310