Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 376 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.1949. Min Range: -1.1949

Max Act: 1.1949. Min Act: -0.0001

Data Index: 1333728 (C4 (Web Text))

Max Activating Token Index: 144

Text #1

Max Range: 1.1949. Min Range: -1.1949

Max Act: 1.1775. Min Act: -0.0001

Data Index: 1302584 (C4 (Web Text))

Max Activating Token Index: 465

Text #2

Max Range: 1.1949. Min Range: -1.1949

Max Act: 1.0562. Min Act: -0.0001

Data Index: 517354 (C4 (Web Text))

Max Activating Token Index: 668

Text #3

Max Range: 1.1949. Min Range: -1.1949

Max Act: 1.1261. Min Act: -0.0001

Data Index: 127308 (C4 (Web Text))

Max Activating Token Index: 846

Text #4

Max Range: 1.1949. Min Range: -1.1949

Max Act: 1.1763. Min Act: -0.0001

Data Index: 1227986 (C4 (Web Text))

Max Activating Token Index: 918

Text #5

Max Range: 1.1949. Min Range: -1.1949

Max Act: 1.0967. Min Act: -0.0001

Data Index: 97915 (C4 (Web Text))

Max Activating Token Index: 733

Text #6

Max Range: 1.1949. Min Range: -1.1949

Max Act: 1.0549. Min Act: -0.0001

Data Index: 993081 (C4 (Web Text))

Max Activating Token Index: 951

Text #7

Max Range: 1.1949. Min Range: -1.1949

Max Act: 1.1102. Min Act: -0.0001

Data Index: 495416 (C4 (Web Text))

Max Activating Token Index: 1019

Text #8

Max Range: 1.1949. Min Range: -1.1949

Max Act: 0.9743. Min Act: -0.0001

Data Index: 360940 (C4 (Web Text))

Max Activating Token Index: 106

Text #9

Max Range: 1.1949. Min Range: -1.1949

Max Act: 0.9882. Min Act: -0.0001

Data Index: 1279421 (C4 (Web Text))

Max Activating Token Index: 65

Text #10

Max Range: 1.1949. Min Range: -1.1949

Max Act: 1.0163. Min Act: -0.0001

Data Index: 601736 (C4 (Web Text))

Max Activating Token Index: 537

Text #11

Max Range: 1.1949. Min Range: -1.1949

Max Act: 1.0704. Min Act: -0.0001

Data Index: 472731 (C4 (Web Text))

Max Activating Token Index: 871

Text #12

Max Range: 1.1949. Min Range: -1.1949

Max Act: 1.0330. Min Act: -0.0001

Data Index: 1028668 (C4 (Web Text))

Max Activating Token Index: 872

Text #13

Max Range: 1.1949. Min Range: -1.1949

Max Act: 0.9624. Min Act: -0.0001

Data Index: 1187008 (C4 (Web Text))

Max Activating Token Index: 54

Text #14

Max Range: 1.1949. Min Range: -1.1949

Max Act: 1.0001. Min Act: -0.0001

Data Index: 153384 (C4 (Web Text))

Max Activating Token Index: 442

Text #15

Max Range: 1.1949. Min Range: -1.1949

Max Act: 0.9944. Min Act: -0.0001

Data Index: 521554 (C4 (Web Text))

Max Activating Token Index: 690

Text #16

Max Range: 1.1949. Min Range: -1.1949

Max Act: 0.9255. Min Act: -0.0001

Data Index: 148656 (C4 (Web Text))

Max Activating Token Index: 482

Text #17

Max Range: 1.1949. Min Range: -1.1949

Max Act: 0.9499. Min Act: -0.0001

Data Index: 550262 (C4 (Web Text))

Max Activating Token Index: 51

Text #18

Max Range: 1.1949. Min Range: -1.1949

Max Act: 1.0572. Min Act: -0.0001

Data Index: 26769 (C4 (Web Text))

Max Activating Token Index: 191

Text #19

Max Range: 1.1949. Min Range: -1.1949

Max Act: 0.9055. Min Act: -0.0001

Data Index: 961892 (C4 (Web Text))

Max Activating Token Index: 837