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

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

Neuron 3328 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0639. Min Range: -1.0639

Max Act: 1.0639. Min Act: -0.0000

Data Index: 1173249 (C4 (Web Text))

Max Activating Token Index: 46

Text #1

Max Range: 1.0639. Min Range: -1.0639

Max Act: 1.0590. Min Act: -0.0000

Data Index: 213609 (C4 (Web Text))

Max Activating Token Index: 94

Text #2

Max Range: 1.0639. Min Range: -1.0639

Max Act: 1.0034. Min Act: -0.0000

Data Index: 116178 (C4 (Web Text))

Max Activating Token Index: 380

Text #3

Max Range: 1.0639. Min Range: -1.0639

Max Act: 0.9840. Min Act: -0.0000

Data Index: 280694 (C4 (Web Text))

Max Activating Token Index: 734

Text #4

Max Range: 1.0639. Min Range: -1.0639

Max Act: 0.9366. Min Act: -0.0000

Data Index: 264277 (C4 (Web Text))

Max Activating Token Index: 288

Text #5

Max Range: 1.0639. Min Range: -1.0639

Max Act: 0.7731. Min Act: -0.0000

Data Index: 952549 (C4 (Web Text))

Max Activating Token Index: 215

Text #6

Max Range: 1.0639. Min Range: -1.0639

Max Act: 0.7917. Min Act: -0.0000

Data Index: 869043 (C4 (Web Text))

Max Activating Token Index: 926

Text #7

Max Range: 1.0639. Min Range: -1.0639

Max Act: 0.7461. Min Act: -0.0000

Data Index: 505836 (C4 (Web Text))

Max Activating Token Index: 531

Text #8

Max Range: 1.0639. Min Range: -1.0639

Max Act: 0.8032. Min Act: -0.0000

Data Index: 102441 (C4 (Web Text))

Max Activating Token Index: 500

Text #9

Max Range: 1.0639. Min Range: -1.0639

Max Act: 0.7593. Min Act: -0.0000

Data Index: 383886 (C4 (Web Text))

Max Activating Token Index: 927

Text #10

Max Range: 1.0639. Min Range: -1.0639

Max Act: 0.7269. Min Act: -0.0000

Data Index: 913158 (C4 (Web Text))

Max Activating Token Index: 85

Text #11

Max Range: 1.0639. Min Range: -1.0639

Max Act: 0.7246. Min Act: -0.0000

Data Index: 998430 (C4 (Web Text))

Max Activating Token Index: 546

Text #12

Max Range: 1.0639. Min Range: -1.0639

Max Act: 0.5277. Min Act: -0.0000

Data Index: 533224 (C4 (Web Text))

Max Activating Token Index: 639

Text #13

Max Range: 1.0639. Min Range: -1.0639

Max Act: 0.6954. Min Act: -0.0000

Data Index: 157499 (C4 (Web Text))

Max Activating Token Index: 136

Text #14

Max Range: 1.0639. Min Range: -1.0639

Max Act: 0.6949. Min Act: -0.0000

Data Index: 1236777 (C4 (Web Text))

Max Activating Token Index: 789

Text #15

Max Range: 1.0639. Min Range: -1.0639

Max Act: 0.5075. Min Act: -0.0000

Data Index: 1357190 (C4 (Web Text))

Max Activating Token Index: 539

Text #16

Max Range: 1.0639. Min Range: -1.0639

Max Act: 0.6573. Min Act: -0.0000

Data Index: 1086946 (C4 (Web Text))

Max Activating Token Index: 299

Text #17

Max Range: 1.0639. Min Range: -1.0639

Max Act: 0.6768. Min Act: -0.0000

Data Index: 455850 (C4 (Web Text))

Max Activating Token Index: 900

Text #18

Max Range: 1.0639. Min Range: -1.0639

Max Act: 0.5954. Min Act: -0.0000

Data Index: 883405 (C4 (Web Text))

Max Activating Token Index: 97

Text #19

Max Range: 1.0639. Min Range: -1.0639

Max Act: 0.6613. Min Act: -0.0000

Data Index: 15407 (C4 (Web Text))

Max Activating Token Index: 849