Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1566 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 2.9363. Min Range: -2.9363

Max Act: 2.9363. Min Act: -0.0001

Data Index: 787316 (C4 (Web Text))

Max Activating Token Index: 857

Text #1

Max Range: 2.9363. Min Range: -2.9363

Max Act: 2.8040. Min Act: -0.0001

Data Index: 1010361 (C4 (Web Text))

Max Activating Token Index: 601

Text #2

Max Range: 2.9363. Min Range: -2.9363

Max Act: 2.3279. Min Act: -0.0000

Data Index: 1195301 (C4 (Web Text))

Max Activating Token Index: 741

Text #3

Max Range: 2.9363. Min Range: -2.9363

Max Act: 2.5823. Min Act: -0.0001

Data Index: 347174 (C4 (Web Text))

Max Activating Token Index: 621

Text #4

Max Range: 2.9363. Min Range: -2.9363

Max Act: 2.5380. Min Act: -0.0001

Data Index: 1258806 (C4 (Web Text))

Max Activating Token Index: 941

Text #5

Max Range: 2.9363. Min Range: -2.9363

Max Act: 2.3905. Min Act: -0.0001

Data Index: 7264 (C4 (Web Text))

Max Activating Token Index: 147

Text #6

Max Range: 2.9363. Min Range: -2.9363

Max Act: 2.0111. Min Act: -0.0001

Data Index: 972789 (C4 (Web Text))

Max Activating Token Index: 743

Text #7

Max Range: 2.9363. Min Range: -2.9363

Max Act: 1.9666. Min Act: -0.0001

Data Index: 32102 (C4 (Web Text))

Max Activating Token Index: 690

Text #8

Max Range: 2.9363. Min Range: -2.9363

Max Act: 2.1651. Min Act: -0.0000

Data Index: 505184 (C4 (Web Text))

Max Activating Token Index: 816

Text #9

Max Range: 2.9363. Min Range: -2.9363

Max Act: 2.3637. Min Act: -0.0001

Data Index: 904652 (C4 (Web Text))

Max Activating Token Index: 802

Text #10

Max Range: 2.9363. Min Range: -2.9363

Max Act: 1.9789. Min Act: -0.0000

Data Index: 776995 (C4 (Web Text))

Max Activating Token Index: 54

Text #11

Max Range: 2.9363. Min Range: -2.9363

Max Act: 1.9160. Min Act: -0.0000

Data Index: 840554 (C4 (Web Text))

Max Activating Token Index: 370

Text #12

Max Range: 2.9363. Min Range: -2.9363

Max Act: 1.8261. Min Act: -0.0001

Data Index: 1182357 (C4 (Web Text))

Max Activating Token Index: 164

Text #13

Max Range: 2.9363. Min Range: -2.9363

Max Act: 1.8854. Min Act: -0.0000

Data Index: 1044590 (C4 (Web Text))

Max Activating Token Index: 60

Text #14

Max Range: 2.9363. Min Range: -2.9363

Max Act: 1.7799. Min Act: -0.0001

Data Index: 935327 (C4 (Web Text))

Max Activating Token Index: 252

Text #15

Max Range: 2.9363. Min Range: -2.9363

Max Act: 1.7689. Min Act: -0.0001

Data Index: 267783 (C4 (Web Text))

Max Activating Token Index: 40

Text #16

Max Range: 2.9363. Min Range: -2.9363

Max Act: 1.6623. Min Act: -0.0001

Data Index: 49882 (C4 (Web Text))

Max Activating Token Index: 127

Text #17

Max Range: 2.9363. Min Range: -2.9363

Max Act: 1.6677. Min Act: -0.0000

Data Index: 906986 (C4 (Web Text))

Max Activating Token Index: 616

Text #18

Max Range: 2.9363. Min Range: -2.9363

Max Act: 1.8156. Min Act: -0.0001

Data Index: 638891 (C4 (Web Text))

Max Activating Token Index: 205

Text #19

Max Range: 2.9363. Min Range: -2.9363

Max Act: 1.6817. Min Act: -0.0000

Data Index: 52104 (C4 (Web Text))

Max Activating Token Index: 646