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

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

Neuron 992 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6125. Min Range: -0.6125

Max Act: 0.6125. Min Act: -0.0001

Data Index: 366750 (C4 (Web Text))

Max Activating Token Index: 27

Text #1

Max Range: 0.6125. Min Range: -0.6125

Max Act: 0.5223. Min Act: -0.0000

Data Index: 301138 (C4 (Web Text))

Max Activating Token Index: 836

Text #2

Max Range: 0.6125. Min Range: -0.6125

Max Act: 0.4636. Min Act: -0.0000

Data Index: 622345 (C4 (Web Text))

Max Activating Token Index: 691

Text #3

Max Range: 0.6125. Min Range: -0.6125

Max Act: 0.4577. Min Act: -0.0000

Data Index: 1022127 (C4 (Web Text))

Max Activating Token Index: 750

Text #4

Max Range: 0.6125. Min Range: -0.6125

Max Act: 0.4513. Min Act: -0.0001

Data Index: 661972 (C4 (Web Text))

Max Activating Token Index: 323

Text #5

Max Range: 0.6125. Min Range: -0.6125

Max Act: 0.4829. Min Act: -0.0001

Data Index: 275200 (C4 (Web Text))

Max Activating Token Index: 40

Text #6

Max Range: 0.6125. Min Range: -0.6125

Max Act: 0.4599. Min Act: -0.0000

Data Index: 872135 (C4 (Web Text))

Max Activating Token Index: 905

Text #7

Max Range: 0.6125. Min Range: -0.6125

Max Act: 0.4747. Min Act: -0.0001

Data Index: 1243023 (C4 (Web Text))

Max Activating Token Index: 339

Text #8

Max Range: 0.6125. Min Range: -0.6125

Max Act: 0.4727. Min Act: -0.0001

Data Index: 1184159 (C4 (Web Text))

Max Activating Token Index: 9

Text #9

Max Range: 0.6125. Min Range: -0.6125

Max Act: 0.4862. Min Act: -0.0000

Data Index: 1265944 (C4 (Web Text))

Max Activating Token Index: 341

Text #10

Max Range: 0.6125. Min Range: -0.6125

Max Act: 0.4444. Min Act: -0.0000

Data Index: 1114706 (C4 (Web Text))

Max Activating Token Index: 29

Text #11

Max Range: 0.6125. Min Range: -0.6125

Max Act: 0.4496. Min Act: -0.0001

Data Index: 1334421 (C4 (Web Text))

Max Activating Token Index: 997

Text #12

Max Range: 0.6125. Min Range: -0.6125

Max Act: 0.4975. Min Act: -0.0001

Data Index: 441949 (C4 (Web Text))

Max Activating Token Index: 99

Text #13

Max Range: 0.6125. Min Range: -0.6125

Max Act: 0.4433. Min Act: -0.0000

Data Index: 968606 (C4 (Web Text))

Max Activating Token Index: 678

Text #14

Max Range: 0.6125. Min Range: -0.6125

Max Act: 0.4055. Min Act: -0.0001

Data Index: 513756 (C4 (Web Text))

Max Activating Token Index: 50

Text #15

Max Range: 0.6125. Min Range: -0.6125

Max Act: 0.4456. Min Act: -0.0000

Data Index: 427448 (C4 (Web Text))

Max Activating Token Index: 237

Text #16

Max Range: 0.6125. Min Range: -0.6125

Max Act: 0.4264. Min Act: -0.0001

Data Index: 55523 (C4 (Web Text))

Max Activating Token Index: 994

Text #17

Max Range: 0.6125. Min Range: -0.6125

Max Act: 0.4390. Min Act: -0.0001

Data Index: 321291 (C4 (Web Text))

Max Activating Token Index: 843

Text #18

Max Range: 0.6125. Min Range: -0.6125

Max Act: 0.4411. Min Act: -0.0001

Data Index: 586712 (C4 (Web Text))

Max Activating Token Index: 872

Text #19

Max Range: 0.6125. Min Range: -0.6125

Max Act: 0.4164. Min Act: -0.0000

Data Index: 521842 (C4 (Web Text))

Max Activating Token Index: 37