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

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

Neuron 4828 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.8636. Min Range: -4.8636

Max Act: 4.8636. Min Act: -0.0000

Data Index: 899581 (C4 (Web Text))

Max Activating Token Index: 719

Text #1

Max Range: 4.8636. Min Range: -4.8636

Max Act: 4.4186. Min Act: -0.0000

Data Index: 244566 (C4 (Web Text))

Max Activating Token Index: 211

Text #2

Max Range: 4.8636. Min Range: -4.8636

Max Act: 4.6813. Min Act: -0.0000

Data Index: 104290 (C4 (Web Text))

Max Activating Token Index: 247

Text #3

Max Range: 4.8636. Min Range: -4.8636

Max Act: 4.1565. Min Act: -0.0000

Data Index: 735844 (C4 (Web Text))

Max Activating Token Index: 207

Text #4

Max Range: 4.8636. Min Range: -4.8636

Max Act: 3.9574. Min Act: -0.0000

Data Index: 1031939 (C4 (Web Text))

Max Activating Token Index: 670

Text #5

Max Range: 4.8636. Min Range: -4.8636

Max Act: 3.8892. Min Act: -0.0000

Data Index: 1024855 (C4 (Web Text))

Max Activating Token Index: 117

Text #6

Max Range: 4.8636. Min Range: -4.8636

Max Act: 3.9881. Min Act: -0.0000

Data Index: 1234392 (C4 (Web Text))

Max Activating Token Index: 174

Text #7

Max Range: 4.8636. Min Range: -4.8636

Max Act: 3.9058. Min Act: -0.0000

Data Index: 984410 (C4 (Web Text))

Max Activating Token Index: 919

Text #8

Max Range: 4.8636. Min Range: -4.8636

Max Act: 3.7462. Min Act: -0.0000

Data Index: 302309 (C4 (Web Text))

Max Activating Token Index: 506

Text #9

Max Range: 4.8636. Min Range: -4.8636

Max Act: 3.7352. Min Act: -0.0000

Data Index: 737701 (C4 (Web Text))

Max Activating Token Index: 957

Text #10

Max Range: 4.8636. Min Range: -4.8636

Max Act: 3.8691. Min Act: -0.0000

Data Index: 823427 (C4 (Web Text))

Max Activating Token Index: 38

Text #11

Max Range: 4.8636. Min Range: -4.8636

Max Act: 3.8600. Min Act: -0.0000

Data Index: 1001289 (C4 (Web Text))

Max Activating Token Index: 346

Text #12

Max Range: 4.8636. Min Range: -4.8636

Max Act: 3.7082. Min Act: -0.0000

Data Index: 382097 (C4 (Web Text))

Max Activating Token Index: 873

Text #13

Max Range: 4.8636. Min Range: -4.8636

Max Act: 3.8588. Min Act: -0.0000

Data Index: 636824 (C4 (Web Text))

Max Activating Token Index: 957

Text #14

Max Range: 4.8636. Min Range: -4.8636

Max Act: 3.6537. Min Act: -0.0000

Data Index: 1314415 (C4 (Web Text))

Max Activating Token Index: 158

Text #15

Max Range: 4.8636. Min Range: -4.8636

Max Act: 3.6456. Min Act: -0.0000

Data Index: 397392 (C4 (Web Text))

Max Activating Token Index: 860

Text #16

Max Range: 4.8636. Min Range: -4.8636

Max Act: 3.6256. Min Act: -0.0000

Data Index: 99057 (C4 (Web Text))

Max Activating Token Index: 983

Text #17

Max Range: 4.8636. Min Range: -4.8636

Max Act: 3.7436. Min Act: -0.0000

Data Index: 1100492 (C4 (Web Text))

Max Activating Token Index: 807

Text #18

Max Range: 4.8636. Min Range: -4.8636

Max Act: 3.5910. Min Act: -0.0000

Data Index: 1228312 (C4 (Web Text))

Max Activating Token Index: 79

Text #19

Max Range: 4.8636. Min Range: -4.8636

Max Act: 3.5785. Min Act: -0.0000

Data Index: 52790 (C4 (Web Text))

Max Activating Token Index: 508