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

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

Neuron 1435 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: 3.9326. Min Range: -3.9326

Max Act: 3.9326. Min Act: -0.0001

Data Index: 235671 (C4 (Web Text))

Max Activating Token Index: 268

Text #1

Max Range: 3.9326. Min Range: -3.9326

Max Act: 3.0486. Min Act: -0.0000

Data Index: 492114 (C4 (Web Text))

Max Activating Token Index: 610

Text #2

Max Range: 3.9326. Min Range: -3.9326

Max Act: 2.2214. Min Act: -0.0001

Data Index: 908152 (C4 (Web Text))

Max Activating Token Index: 280

Text #3

Max Range: 3.9326. Min Range: -3.9326

Max Act: 2.6027. Min Act: -0.0000

Data Index: 532748 (C4 (Web Text))

Max Activating Token Index: 1011

Text #4

Max Range: 3.9326. Min Range: -3.9326

Max Act: 2.5404. Min Act: -0.0000

Data Index: 1063834 (C4 (Web Text))

Max Activating Token Index: 78

Text #5

Max Range: 3.9326. Min Range: -3.9326

Max Act: 2.4007. Min Act: -0.0000

Data Index: 953866 (C4 (Web Text))

Max Activating Token Index: 787

Text #6

Max Range: 3.9326. Min Range: -3.9326

Max Act: 2.3768. Min Act: -0.0000

Data Index: 30627 (C4 (Web Text))

Max Activating Token Index: 624

Text #7

Max Range: 3.9326. Min Range: -3.9326

Max Act: 2.2406. Min Act: -0.0000

Data Index: 88097 (C4 (Web Text))

Max Activating Token Index: 8

Text #8

Max Range: 3.9326. Min Range: -3.9326

Max Act: 2.2009. Min Act: -0.0000

Data Index: 638116 (C4 (Web Text))

Max Activating Token Index: 416

Text #9

Max Range: 3.9326. Min Range: -3.9326

Max Act: 2.0258. Min Act: -0.0000

Data Index: 539245 (C4 (Web Text))

Max Activating Token Index: 277

Text #10

Max Range: 3.9326. Min Range: -3.9326

Max Act: 2.0056. Min Act: -0.0001

Data Index: 261514 (C4 (Web Text))

Max Activating Token Index: 352

Text #11

Max Range: 3.9326. Min Range: -3.9326

Max Act: 1.9683. Min Act: -0.0000

Data Index: 162523 (C4 (Web Text))

Max Activating Token Index: 639

Text #12

Max Range: 3.9326. Min Range: -3.9326

Max Act: 1.6894. Min Act: -0.0000

Data Index: 676200 (C4 (Web Text))

Max Activating Token Index: 112

Text #13

Max Range: 3.9326. Min Range: -3.9326

Max Act: 1.8131. Min Act: -0.0000

Data Index: 1012728 (C4 (Web Text))

Max Activating Token Index: 947

Text #14

Max Range: 3.9326. Min Range: -3.9326

Max Act: 1.6706. Min Act: -0.0000

Data Index: 1252992 (C4 (Web Text))

Max Activating Token Index: 984

Text #15

Max Range: 3.9326. Min Range: -3.9326

Max Act: 1.9420. Min Act: -0.0000

Data Index: 1000105 (C4 (Web Text))

Max Activating Token Index: 949

Text #16

Max Range: 3.9326. Min Range: -3.9326

Max Act: 1.5261. Min Act: -0.0000

Data Index: 1018438 (C4 (Web Text))

Max Activating Token Index: 233

Text #17

Max Range: 3.9326. Min Range: -3.9326

Max Act: 1.8382. Min Act: -0.0000

Data Index: 827837 (C4 (Web Text))

Max Activating Token Index: 562

Text #18

Max Range: 3.9326. Min Range: -3.9326

Max Act: 1.7189. Min Act: -0.0000

Data Index: 991157 (C4 (Web Text))

Max Activating Token Index: 9

Text #19

Max Range: 3.9326. Min Range: -3.9326

Max Act: 1.6919. Min Act: -0.0000

Data Index: 1273007 (C4 (Web Text))

Max Activating Token Index: 576