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

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

Neuron 674 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.0742. Min Range: -3.0742

Max Act: 3.0742. Min Act: -0.0000

Data Index: 836783 (C4 (Web Text))

Max Activating Token Index: 916

Text #1

Max Range: 3.0742. Min Range: -3.0742

Max Act: 2.2105. Min Act: -0.0000

Data Index: 584218 (C4 (Web Text))

Max Activating Token Index: 555

Text #2

Max Range: 3.0742. Min Range: -3.0742

Max Act: 2.0710. Min Act: -0.0000

Data Index: 1265490 (C4 (Web Text))

Max Activating Token Index: 699

Text #3

Max Range: 3.0742. Min Range: -3.0742

Max Act: 2.2187. Min Act: -0.0000

Data Index: 197812 (C4 (Web Text))

Max Activating Token Index: 322

Text #4

Max Range: 3.0742. Min Range: -3.0742

Max Act: 2.3064. Min Act: -0.0000

Data Index: 330551 (C4 (Web Text))

Max Activating Token Index: 855

Text #5

Max Range: 3.0742. Min Range: -3.0742

Max Act: 2.0337. Min Act: -0.0000

Data Index: 1181737 (C4 (Web Text))

Max Activating Token Index: 582

Text #6

Max Range: 3.0742. Min Range: -3.0742

Max Act: 1.9286. Min Act: -0.0000

Data Index: 865954 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 3.0742. Min Range: -3.0742

Max Act: 2.0284. Min Act: -0.0000

Data Index: 773248 (C4 (Web Text))

Max Activating Token Index: 796

Text #8

Max Range: 3.0742. Min Range: -3.0742

Max Act: 1.9687. Min Act: -0.0000

Data Index: 1089122 (C4 (Web Text))

Max Activating Token Index: 1021

Text #9

Max Range: 3.0742. Min Range: -3.0742

Max Act: 1.8347. Min Act: -0.0000

Data Index: 278219 (C4 (Web Text))

Max Activating Token Index: 1011

Text #10

Max Range: 3.0742. Min Range: -3.0742

Max Act: 1.9406. Min Act: -0.0000

Data Index: 1188678 (C4 (Web Text))

Max Activating Token Index: 697

Text #11

Max Range: 3.0742. Min Range: -3.0742

Max Act: 1.9169. Min Act: -0.0000

Data Index: 973508 (C4 (Web Text))

Max Activating Token Index: 438

Text #12

Max Range: 3.0742. Min Range: -3.0742

Max Act: 1.6355. Min Act: -0.0000

Data Index: 1338796 (C4 (Web Text))

Max Activating Token Index: 252

Text #13

Max Range: 3.0742. Min Range: -3.0742

Max Act: 1.8755. Min Act: -0.0000

Data Index: 1353326 (C4 (Web Text))

Max Activating Token Index: 802

Text #14

Max Range: 3.0742. Min Range: -3.0742

Max Act: 1.7645. Min Act: -0.0000

Data Index: 821790 (C4 (Web Text))

Max Activating Token Index: 785

Text #15

Max Range: 3.0742. Min Range: -3.0742

Max Act: 1.8435. Min Act: -0.0000

Data Index: 461295 (C4 (Web Text))

Max Activating Token Index: 726

Text #16

Max Range: 3.0742. Min Range: -3.0742

Max Act: 1.7435. Min Act: -0.0000

Data Index: 1243176 (C4 (Web Text))

Max Activating Token Index: 798

Text #17

Max Range: 3.0742. Min Range: -3.0742

Max Act: 1.9375. Min Act: -0.0000

Data Index: 626270 (C4 (Web Text))

Max Activating Token Index: 756

Text #18

Max Range: 3.0742. Min Range: -3.0742

Max Act: 1.5972. Min Act: -0.0000

Data Index: 917287 (C4 (Web Text))

Max Activating Token Index: 203

Text #19

Max Range: 3.0742. Min Range: -3.0742

Max Act: 1.6309. Min Act: -0.0000

Data Index: 1305034 (C4 (Web Text))

Max Activating Token Index: 107