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

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

Neuron 1758 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: 1.2054. Min Range: -1.2054

Max Act: 1.2054. Min Act: -0.0000

Data Index: 1172527 (C4 (Web Text))

Max Activating Token Index: 782

Text #1

Max Range: 1.2054. Min Range: -1.2054

Max Act: 1.1228. Min Act: -0.0000

Data Index: 1259123 (C4 (Web Text))

Max Activating Token Index: 816

Text #2

Max Range: 1.2054. Min Range: -1.2054

Max Act: 0.9745. Min Act: -0.0001

Data Index: 173353 (C4 (Web Text))

Max Activating Token Index: 115

Text #3

Max Range: 1.2054. Min Range: -1.2054

Max Act: 1.0369. Min Act: -0.0001

Data Index: 835175 (C4 (Web Text))

Max Activating Token Index: 461

Text #4

Max Range: 1.2054. Min Range: -1.2054

Max Act: 0.9556. Min Act: -0.0001

Data Index: 443767 (C4 (Web Text))

Max Activating Token Index: 185

Text #5

Max Range: 1.2054. Min Range: -1.2054

Max Act: 0.9070. Min Act: -0.0001

Data Index: 698352 (C4 (Web Text))

Max Activating Token Index: 662

Text #6

Max Range: 1.2054. Min Range: -1.2054

Max Act: 0.9000. Min Act: -0.0001

Data Index: 1226395 (C4 (Web Text))

Max Activating Token Index: 830

Text #7

Max Range: 1.2054. Min Range: -1.2054

Max Act: 0.9126. Min Act: -0.0000

Data Index: 481001 (C4 (Web Text))

Max Activating Token Index: 963

Text #8

Max Range: 1.2054. Min Range: -1.2054

Max Act: 0.8735. Min Act: -0.0001

Data Index: 872936 (C4 (Web Text))

Max Activating Token Index: 735

Text #9

Max Range: 1.2054. Min Range: -1.2054

Max Act: 0.8932. Min Act: -0.0001

Data Index: 481247 (C4 (Web Text))

Max Activating Token Index: 749

Text #10

Max Range: 1.2054. Min Range: -1.2054

Max Act: 0.8303. Min Act: -0.0001

Data Index: 1037823 (C4 (Web Text))

Max Activating Token Index: 578

Text #11

Max Range: 1.2054. Min Range: -1.2054

Max Act: 0.8302. Min Act: -0.0001

Data Index: 1279942 (C4 (Web Text))

Max Activating Token Index: 1004

Text #12

Max Range: 1.2054. Min Range: -1.2054

Max Act: 0.8241. Min Act: -0.0000

Data Index: 818300 (C4 (Web Text))

Max Activating Token Index: 941

Text #13

Max Range: 1.2054. Min Range: -1.2054

Max Act: 0.8418. Min Act: -0.0001

Data Index: 923198 (C4 (Web Text))

Max Activating Token Index: 839

Text #14

Max Range: 1.2054. Min Range: -1.2054

Max Act: 0.7881. Min Act: -0.0000

Data Index: 639710 (C4 (Web Text))

Max Activating Token Index: 811

Text #15

Max Range: 1.2054. Min Range: -1.2054

Max Act: 0.8762. Min Act: -0.0001

Data Index: 191889 (C4 (Web Text))

Max Activating Token Index: 585

Text #16

Max Range: 1.2054. Min Range: -1.2054

Max Act: 0.8024. Min Act: -0.0001

Data Index: 90971 (C4 (Web Text))

Max Activating Token Index: 283

Text #17

Max Range: 1.2054. Min Range: -1.2054

Max Act: 0.8099. Min Act: -0.0000

Data Index: 744529 (C4 (Web Text))

Max Activating Token Index: 495

Text #18

Max Range: 1.2054. Min Range: -1.2054

Max Act: 0.8102. Min Act: -0.0000

Data Index: 27367 (C4 (Web Text))

Max Activating Token Index: 635

Text #19

Max Range: 1.2054. Min Range: -1.2054

Max Act: 0.8043. Min Act: -0.0001

Data Index: 1148063 (C4 (Web Text))

Max Activating Token Index: 801