Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4699 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.9442. Min Range: -2.9442

Max Act: 2.9442. Min Act: -0.0000

Data Index: 447176 (C4 (Web Text))

Max Activating Token Index: 423

Text #1

Max Range: 2.9442. Min Range: -2.9442

Max Act: 2.7662. Min Act: -0.0000

Data Index: 909764 (C4 (Web Text))

Max Activating Token Index: 1003

Text #2

Max Range: 2.9442. Min Range: -2.9442

Max Act: 2.6705. Min Act: -0.0000

Data Index: 274651 (C4 (Web Text))

Max Activating Token Index: 789

Text #3

Max Range: 2.9442. Min Range: -2.9442

Max Act: 2.3636. Min Act: -0.0000

Data Index: 649382 (C4 (Web Text))

Max Activating Token Index: 803

Text #4

Max Range: 2.9442. Min Range: -2.9442

Max Act: 2.4714. Min Act: -0.0000

Data Index: 888234 (C4 (Web Text))

Max Activating Token Index: 726

Text #5

Max Range: 2.9442. Min Range: -2.9442

Max Act: 2.3318. Min Act: -0.0000

Data Index: 858295 (C4 (Web Text))

Max Activating Token Index: 161

Text #6

Max Range: 2.9442. Min Range: -2.9442

Max Act: 2.2880. Min Act: -0.0000

Data Index: 1081659 (C4 (Web Text))

Max Activating Token Index: 912

Text #7

Max Range: 2.9442. Min Range: -2.9442

Max Act: 2.2627. Min Act: -0.0000

Data Index: 418375 (C4 (Web Text))

Max Activating Token Index: 878

Text #8

Max Range: 2.9442. Min Range: -2.9442

Max Act: 2.0069. Min Act: -0.0000

Data Index: 1213862 (C4 (Web Text))

Max Activating Token Index: 152

Text #9

Max Range: 2.9442. Min Range: -2.9442

Max Act: 1.5043. Min Act: -0.0000

Data Index: 623074 (C4 (Web Text))

Max Activating Token Index: 640

Text #10

Max Range: 2.9442. Min Range: -2.9442

Max Act: 1.5289. Min Act: -0.0000

Data Index: 626944 (C4 (Web Text))

Max Activating Token Index: 109

Text #11

Max Range: 2.9442. Min Range: -2.9442

Max Act: 1.4957. Min Act: -0.0000

Data Index: 648595 (C4 (Web Text))

Max Activating Token Index: 122

Text #12

Max Range: 2.9442. Min Range: -2.9442

Max Act: 1.3711. Min Act: -0.0000

Data Index: 1135914 (C4 (Web Text))

Max Activating Token Index: 111

Text #13

Max Range: 2.9442. Min Range: -2.9442

Max Act: 1.4070. Min Act: -0.0000

Data Index: 944439 (C4 (Web Text))

Max Activating Token Index: 85

Text #14

Max Range: 2.9442. Min Range: -2.9442

Max Act: 1.2659. Min Act: -0.0000

Data Index: 1206267 (C4 (Web Text))

Max Activating Token Index: 838

Text #15

Max Range: 2.9442. Min Range: -2.9442

Max Act: 1.2853. Min Act: -0.0000

Data Index: 777981 (C4 (Web Text))

Max Activating Token Index: 973

Text #16

Max Range: 2.9442. Min Range: -2.9442

Max Act: 1.1806. Min Act: -0.0000

Data Index: 805456 (C4 (Web Text))

Max Activating Token Index: 888

Text #17

Max Range: 2.9442. Min Range: -2.9442

Max Act: 1.3148. Min Act: -0.0000

Data Index: 1277713 (C4 (Web Text))

Max Activating Token Index: 871

Text #18

Max Range: 2.9442. Min Range: -2.9442

Max Act: 1.2343. Min Act: -0.0000

Data Index: 961381 (C4 (Web Text))

Max Activating Token Index: 781

Text #19

Max Range: 2.9442. Min Range: -2.9442

Max Act: 1.2669. Min Act: -0.0000

Data Index: 517800 (C4 (Web Text))

Max Activating Token Index: 861