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

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

Neuron 3008 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5927. Min Range: -1.5927

Max Act: 1.5927. Min Act: -0.0001

Data Index: 43853 (C4 (Web Text))

Max Activating Token Index: 381

Text #1

Max Range: 1.5927. Min Range: -1.5927

Max Act: 1.2516. Min Act: -0.0001

Data Index: 1076228 (C4 (Web Text))

Max Activating Token Index: 943

Text #2

Max Range: 1.5927. Min Range: -1.5927

Max Act: 1.2123. Min Act: -0.0001

Data Index: 552423 (C4 (Web Text))

Max Activating Token Index: 108

Text #3

Max Range: 1.5927. Min Range: -1.5927

Max Act: 1.2798. Min Act: -0.0001

Data Index: 1513504 (Python Code)

Max Activating Token Index: 764

Text #4

Max Range: 1.5927. Min Range: -1.5927

Max Act: 1.1536. Min Act: -0.0001

Data Index: 550092 (C4 (Web Text))

Max Activating Token Index: 501

Text #5

Max Range: 1.5927. Min Range: -1.5927

Max Act: 1.0311. Min Act: -0.0001

Data Index: 211908 (C4 (Web Text))

Max Activating Token Index: 11

Text #6

Max Range: 1.5927. Min Range: -1.5927

Max Act: 1.0906. Min Act: -0.0001

Data Index: 556551 (C4 (Web Text))

Max Activating Token Index: 557

Text #7

Max Range: 1.5927. Min Range: -1.5927

Max Act: 0.8994. Min Act: -0.0001

Data Index: 1047500 (C4 (Web Text))

Max Activating Token Index: 74

Text #8

Max Range: 1.5927. Min Range: -1.5927

Max Act: 1.0838. Min Act: -0.0001

Data Index: 1147214 (C4 (Web Text))

Max Activating Token Index: 391

Text #9

Max Range: 1.5927. Min Range: -1.5927

Max Act: 0.9964. Min Act: -0.0001

Data Index: 590312 (C4 (Web Text))

Max Activating Token Index: 243

Text #10

Max Range: 1.5927. Min Range: -1.5927

Max Act: 1.0775. Min Act: -0.0000

Data Index: 662764 (C4 (Web Text))

Max Activating Token Index: 464

Text #11

Max Range: 1.5927. Min Range: -1.5927

Max Act: 0.8799. Min Act: -0.0001

Data Index: 1316684 (C4 (Web Text))

Max Activating Token Index: 660

Text #12

Max Range: 1.5927. Min Range: -1.5927

Max Act: 1.1033. Min Act: -0.0001

Data Index: 1179960 (C4 (Web Text))

Max Activating Token Index: 126

Text #13

Max Range: 1.5927. Min Range: -1.5927

Max Act: 1.0348. Min Act: -0.0001

Data Index: 620854 (C4 (Web Text))

Max Activating Token Index: 481

Text #14

Max Range: 1.5927. Min Range: -1.5927

Max Act: 1.0270. Min Act: -0.0001

Data Index: 948631 (C4 (Web Text))

Max Activating Token Index: 101

Text #15

Max Range: 1.5927. Min Range: -1.5927

Max Act: 1.0250. Min Act: -0.0001

Data Index: 371365 (C4 (Web Text))

Max Activating Token Index: 739

Text #16

Max Range: 1.5927. Min Range: -1.5927

Max Act: 1.0484. Min Act: -0.0001

Data Index: 663983 (C4 (Web Text))

Max Activating Token Index: 430

Text #17

Max Range: 1.5927. Min Range: -1.5927

Max Act: 1.2185. Min Act: -0.0001

Data Index: 113791 (C4 (Web Text))

Max Activating Token Index: 190

Text #18

Max Range: 1.5927. Min Range: -1.5927

Max Act: 0.9526. Min Act: -0.0001

Data Index: 201768 (C4 (Web Text))

Max Activating Token Index: 53

Text #19

Max Range: 1.5927. Min Range: -1.5927

Max Act: 0.9310. Min Act: -0.0001

Data Index: 737751 (C4 (Web Text))

Max Activating Token Index: 192