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

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

Neuron 3717 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6975. Min Range: -1.6975

Max Act: 1.6295. Min Act: -0.0002

Data Index: 887281 (C4 (Web Text))

Max Activating Token Index: 525

Text #1

Max Range: 1.6975. Min Range: -1.6975

Max Act: 1.6975. Min Act: -0.0002

Data Index: 1228648 (C4 (Web Text))

Max Activating Token Index: 1019

Text #2

Max Range: 1.6975. Min Range: -1.6975

Max Act: 1.5620. Min Act: -0.0001

Data Index: 469761 (C4 (Web Text))

Max Activating Token Index: 550

Text #3

Max Range: 1.6975. Min Range: -1.6975

Max Act: 1.4267. Min Act: -0.0002

Data Index: 1048130 (C4 (Web Text))

Max Activating Token Index: 819

Text #4

Max Range: 1.6975. Min Range: -1.6975

Max Act: 1.3750. Min Act: -0.0002

Data Index: 736758 (C4 (Web Text))

Max Activating Token Index: 621

Text #5

Max Range: 1.6975. Min Range: -1.6975

Max Act: 1.1850. Min Act: -0.0002

Data Index: 942359 (C4 (Web Text))

Max Activating Token Index: 695

Text #6

Max Range: 1.6975. Min Range: -1.6975

Max Act: 1.1410. Min Act: -0.0002

Data Index: 65040 (C4 (Web Text))

Max Activating Token Index: 698

Text #7

Max Range: 1.6975. Min Range: -1.6975

Max Act: 1.0322. Min Act: -0.0002

Data Index: 189792 (C4 (Web Text))

Max Activating Token Index: 853

Text #8

Max Range: 1.6975. Min Range: -1.6975

Max Act: 1.0886. Min Act: -0.0001

Data Index: 189732 (C4 (Web Text))

Max Activating Token Index: 221

Text #9

Max Range: 1.6975. Min Range: -1.6975

Max Act: 0.9825. Min Act: -0.0002

Data Index: 282137 (C4 (Web Text))

Max Activating Token Index: 119

Text #10

Max Range: 1.6975. Min Range: -1.6975

Max Act: 0.9544. Min Act: -0.0002

Data Index: 535181 (C4 (Web Text))

Max Activating Token Index: 938

Text #11

Max Range: 1.6975. Min Range: -1.6975

Max Act: 0.9749. Min Act: -0.0001

Data Index: 436896 (C4 (Web Text))

Max Activating Token Index: 327

Text #12

Max Range: 1.6975. Min Range: -1.6975

Max Act: 0.9508. Min Act: -0.0001

Data Index: 743941 (C4 (Web Text))

Max Activating Token Index: 226

Text #13

Max Range: 1.6975. Min Range: -1.6975

Max Act: 0.8801. Min Act: -0.0002

Data Index: 1333840 (C4 (Web Text))

Max Activating Token Index: 396

Text #14

Max Range: 1.6975. Min Range: -1.6975

Max Act: 0.9523. Min Act: -0.0002

Data Index: 30849 (C4 (Web Text))

Max Activating Token Index: 598

Text #15

Max Range: 1.6975. Min Range: -1.6975

Max Act: 0.9586. Min Act: -0.0002

Data Index: 1289564 (C4 (Web Text))

Max Activating Token Index: 681

Text #16

Max Range: 1.6975. Min Range: -1.6975

Max Act: 0.8705. Min Act: -0.0001

Data Index: 883023 (C4 (Web Text))

Max Activating Token Index: 765

Text #17

Max Range: 1.6975. Min Range: -1.6975

Max Act: 0.9159. Min Act: -0.0002

Data Index: 1271304 (C4 (Web Text))

Max Activating Token Index: 361

Text #18

Max Range: 1.6975. Min Range: -1.6975

Max Act: 0.9148. Min Act: -0.0002

Data Index: 1122537 (C4 (Web Text))

Max Activating Token Index: 121

Text #19

Max Range: 1.6975. Min Range: -1.6975

Max Act: 0.9397. Min Act: -0.0002

Data Index: 234163 (C4 (Web Text))

Max Activating Token Index: 184