Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3674 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.7174. Min Range: -0.7174

Max Act: 0.7174. Min Act: -0.0000

Data Index: 720879 (C4 (Web Text))

Max Activating Token Index: 458

Text #1

Max Range: 0.7174. Min Range: -0.7174

Max Act: 0.6421. Min Act: -0.0000

Data Index: 401638 (C4 (Web Text))

Max Activating Token Index: 1012

Text #2

Max Range: 0.7174. Min Range: -0.7174

Max Act: 0.6693. Min Act: -0.0000

Data Index: 151313 (C4 (Web Text))

Max Activating Token Index: 328

Text #3

Max Range: 0.7174. Min Range: -0.7174

Max Act: 0.5206. Min Act: -0.0000

Data Index: 771024 (C4 (Web Text))

Max Activating Token Index: 717

Text #4

Max Range: 0.7174. Min Range: -0.7174

Max Act: 0.5399. Min Act: -0.0000

Data Index: 1047712 (C4 (Web Text))

Max Activating Token Index: 470

Text #5

Max Range: 0.7174. Min Range: -0.7174

Max Act: 0.5392. Min Act: -0.0000

Data Index: 1014125 (C4 (Web Text))

Max Activating Token Index: 259

Text #6

Max Range: 0.7174. Min Range: -0.7174

Max Act: 0.4980. Min Act: -0.0000

Data Index: 96333 (C4 (Web Text))

Max Activating Token Index: 794

Text #7

Max Range: 0.7174. Min Range: -0.7174

Max Act: 0.4561. Min Act: -0.0000

Data Index: 634139 (C4 (Web Text))

Max Activating Token Index: 317

Text #8

Max Range: 0.7174. Min Range: -0.7174

Max Act: 0.5054. Min Act: -0.0000

Data Index: 1081025 (C4 (Web Text))

Max Activating Token Index: 806

Text #9

Max Range: 0.7174. Min Range: -0.7174

Max Act: 0.4735. Min Act: -0.0000

Data Index: 1286237 (C4 (Web Text))

Max Activating Token Index: 534

Text #10

Max Range: 0.7174. Min Range: -0.7174

Max Act: 0.4811. Min Act: -0.0000

Data Index: 519092 (C4 (Web Text))

Max Activating Token Index: 973

Text #11

Max Range: 0.7174. Min Range: -0.7174

Max Act: 0.4813. Min Act: -0.0000

Data Index: 935658 (C4 (Web Text))

Max Activating Token Index: 1020

Text #12

Max Range: 0.7174. Min Range: -0.7174

Max Act: 0.4937. Min Act: -0.0000

Data Index: 490066 (C4 (Web Text))

Max Activating Token Index: 1017

Text #13

Max Range: 0.7174. Min Range: -0.7174

Max Act: 0.4783. Min Act: -0.0000

Data Index: 1347846 (C4 (Web Text))

Max Activating Token Index: 1007

Text #14

Max Range: 0.7174. Min Range: -0.7174

Max Act: 0.4977. Min Act: -0.0000

Data Index: 1186083 (C4 (Web Text))

Max Activating Token Index: 912

Text #15

Max Range: 0.7174. Min Range: -0.7174

Max Act: 0.4761. Min Act: -0.0000

Data Index: 120016 (C4 (Web Text))

Max Activating Token Index: 904

Text #16

Max Range: 0.7174. Min Range: -0.7174

Max Act: 0.4889. Min Act: -0.0000

Data Index: 873146 (C4 (Web Text))

Max Activating Token Index: 729

Text #17

Max Range: 0.7174. Min Range: -0.7174

Max Act: 0.4733. Min Act: -0.0000

Data Index: 1242055 (C4 (Web Text))

Max Activating Token Index: 920

Text #18

Max Range: 0.7174. Min Range: -0.7174

Max Act: 0.4706. Min Act: -0.0000

Data Index: 1259197 (C4 (Web Text))

Max Activating Token Index: 723

Text #19

Max Range: 0.7174. Min Range: -0.7174

Max Act: 0.4981. Min Act: -0.0000

Data Index: 1070174 (C4 (Web Text))

Max Activating Token Index: 359