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

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

Neuron 685 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: 1.0004. Min Range: -1.0004

Max Act: 1.0004. Min Act: -0.0000

Data Index: 587048 (C4 (Web Text))

Max Activating Token Index: 366

Text #1

Max Range: 1.0004. Min Range: -1.0004

Max Act: 0.8967. Min Act: -0.0000

Data Index: 843787 (C4 (Web Text))

Max Activating Token Index: 427

Text #2

Max Range: 1.0004. Min Range: -1.0004

Max Act: 0.8333. Min Act: -0.0001

Data Index: 226176 (C4 (Web Text))

Max Activating Token Index: 937

Text #3

Max Range: 1.0004. Min Range: -1.0004

Max Act: 0.8064. Min Act: -0.0000

Data Index: 360837 (C4 (Web Text))

Max Activating Token Index: 671

Text #4

Max Range: 1.0004. Min Range: -1.0004

Max Act: 0.7623. Min Act: -0.0000

Data Index: 46617 (C4 (Web Text))

Max Activating Token Index: 142

Text #5

Max Range: 1.0004. Min Range: -1.0004

Max Act: 0.7914. Min Act: -0.0000

Data Index: 136040 (C4 (Web Text))

Max Activating Token Index: 952

Text #6

Max Range: 1.0004. Min Range: -1.0004

Max Act: 0.7786. Min Act: -0.0000

Data Index: 1099667 (C4 (Web Text))

Max Activating Token Index: 334

Text #7

Max Range: 1.0004. Min Range: -1.0004

Max Act: 0.7289. Min Act: -0.0000

Data Index: 389550 (C4 (Web Text))

Max Activating Token Index: 697

Text #8

Max Range: 1.0004. Min Range: -1.0004

Max Act: 0.7661. Min Act: -0.0000

Data Index: 1219850 (C4 (Web Text))

Max Activating Token Index: 759

Text #9

Max Range: 1.0004. Min Range: -1.0004

Max Act: 0.7630. Min Act: -0.0000

Data Index: 1067431 (C4 (Web Text))

Max Activating Token Index: 615

Text #10

Max Range: 1.0004. Min Range: -1.0004

Max Act: 0.7351. Min Act: -0.0001

Data Index: 1212410 (C4 (Web Text))

Max Activating Token Index: 86

Text #11

Max Range: 1.0004. Min Range: -1.0004

Max Act: 0.7034. Min Act: -0.0000

Data Index: 1218763 (C4 (Web Text))

Max Activating Token Index: 213

Text #12

Max Range: 1.0004. Min Range: -1.0004

Max Act: 0.6802. Min Act: -0.0000

Data Index: 356707 (C4 (Web Text))

Max Activating Token Index: 359

Text #13

Max Range: 1.0004. Min Range: -1.0004

Max Act: 0.7343. Min Act: -0.0000

Data Index: 926675 (C4 (Web Text))

Max Activating Token Index: 601

Text #14

Max Range: 1.0004. Min Range: -1.0004

Max Act: 0.7012. Min Act: -0.0001

Data Index: 1206921 (C4 (Web Text))

Max Activating Token Index: 813

Text #15

Max Range: 1.0004. Min Range: -1.0004

Max Act: 0.7216. Min Act: -0.0001

Data Index: 650746 (C4 (Web Text))

Max Activating Token Index: 854

Text #16

Max Range: 1.0004. Min Range: -1.0004

Max Act: 0.7138. Min Act: -0.0000

Data Index: 1027958 (C4 (Web Text))

Max Activating Token Index: 419

Text #17

Max Range: 1.0004. Min Range: -1.0004

Max Act: 0.6512. Min Act: 0.0000

Data Index: 1073440 (C4 (Web Text))

Max Activating Token Index: 1017

Text #18

Max Range: 1.0004. Min Range: -1.0004

Max Act: 0.6888. Min Act: -0.0000

Data Index: 1306647 (C4 (Web Text))

Max Activating Token Index: 64

Text #19

Max Range: 1.0004. Min Range: -1.0004

Max Act: 0.6556. Min Act: -0.0001

Data Index: 1149567 (C4 (Web Text))

Max Activating Token Index: 1008