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

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

Neuron 5106 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: 0.8834. Min Range: -0.8834

Max Act: 0.8670. Min Act: -0.0001

Data Index: 441873 (C4 (Web Text))

Max Activating Token Index: 64

Text #1

Max Range: 0.8834. Min Range: -0.8834

Max Act: 0.8834. Min Act: -0.0001

Data Index: 1043176 (C4 (Web Text))

Max Activating Token Index: 485

Text #2

Max Range: 0.8834. Min Range: -0.8834

Max Act: 0.8517. Min Act: -0.0001

Data Index: 279574 (C4 (Web Text))

Max Activating Token Index: 584

Text #3

Max Range: 0.8834. Min Range: -0.8834

Max Act: 0.8125. Min Act: -0.0001

Data Index: 1290634 (C4 (Web Text))

Max Activating Token Index: 749

Text #4

Max Range: 0.8834. Min Range: -0.8834

Max Act: 0.8636. Min Act: -0.0001

Data Index: 788240 (C4 (Web Text))

Max Activating Token Index: 552

Text #5

Max Range: 0.8834. Min Range: -0.8834

Max Act: 0.7967. Min Act: -0.0001

Data Index: 725606 (C4 (Web Text))

Max Activating Token Index: 472

Text #6

Max Range: 0.8834. Min Range: -0.8834

Max Act: 0.8180. Min Act: -0.0001

Data Index: 412202 (C4 (Web Text))

Max Activating Token Index: 645

Text #7

Max Range: 0.8834. Min Range: -0.8834

Max Act: 0.8223. Min Act: -0.0001

Data Index: 1244615 (C4 (Web Text))

Max Activating Token Index: 328

Text #8

Max Range: 0.8834. Min Range: -0.8834

Max Act: 0.8183. Min Act: -0.0001

Data Index: 444118 (C4 (Web Text))

Max Activating Token Index: 96

Text #9

Max Range: 0.8834. Min Range: -0.8834

Max Act: 0.8035. Min Act: -0.0001

Data Index: 749885 (C4 (Web Text))

Max Activating Token Index: 325

Text #10

Max Range: 0.8834. Min Range: -0.8834

Max Act: 0.7782. Min Act: -0.0001

Data Index: 786930 (C4 (Web Text))

Max Activating Token Index: 808

Text #11

Max Range: 0.8834. Min Range: -0.8834

Max Act: 0.7922. Min Act: -0.0001

Data Index: 38296 (C4 (Web Text))

Max Activating Token Index: 293

Text #12

Max Range: 0.8834. Min Range: -0.8834

Max Act: 0.7250. Min Act: -0.0001

Data Index: 341155 (C4 (Web Text))

Max Activating Token Index: 161

Text #13

Max Range: 0.8834. Min Range: -0.8834

Max Act: 0.7384. Min Act: -0.0001

Data Index: 304045 (C4 (Web Text))

Max Activating Token Index: 158

Text #14

Max Range: 0.8834. Min Range: -0.8834

Max Act: 0.7664. Min Act: -0.0001

Data Index: 40236 (C4 (Web Text))

Max Activating Token Index: 140

Text #15

Max Range: 0.8834. Min Range: -0.8834

Max Act: 0.7741. Min Act: -0.0001

Data Index: 77245 (C4 (Web Text))

Max Activating Token Index: 476

Text #16

Max Range: 0.8834. Min Range: -0.8834

Max Act: 0.8011. Min Act: -0.0001

Data Index: 17567 (C4 (Web Text))

Max Activating Token Index: 65

Text #17

Max Range: 0.8834. Min Range: -0.8834

Max Act: 0.7514. Min Act: -0.0001

Data Index: 269081 (C4 (Web Text))

Max Activating Token Index: 86

Text #18

Max Range: 0.8834. Min Range: -0.8834

Max Act: 0.7726. Min Act: -0.0001

Data Index: 932603 (C4 (Web Text))

Max Activating Token Index: 204

Text #19

Max Range: 0.8834. Min Range: -0.8834

Max Act: 0.7719. Min Act: -0.0001

Data Index: 813554 (C4 (Web Text))

Max Activating Token Index: 100