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

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

Neuron 2622 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9924. Min Range: -2.9924

Max Act: 2.9924. Min Act: -0.0000

Data Index: 585654 (C4 (Web Text))

Max Activating Token Index: 254

Text #1

Max Range: 2.9924. Min Range: -2.9924

Max Act: 2.7792. Min Act: -0.0000

Data Index: 1021189 (C4 (Web Text))

Max Activating Token Index: 558

Text #2

Max Range: 2.9924. Min Range: -2.9924

Max Act: 2.4986. Min Act: -0.0000

Data Index: 163657 (C4 (Web Text))

Max Activating Token Index: 554

Text #3

Max Range: 2.9924. Min Range: -2.9924

Max Act: 2.6825. Min Act: -0.0000

Data Index: 1199088 (C4 (Web Text))

Max Activating Token Index: 245

Text #4

Max Range: 2.9924. Min Range: -2.9924

Max Act: 2.6769. Min Act: -0.0000

Data Index: 1344078 (C4 (Web Text))

Max Activating Token Index: 6

Text #5

Max Range: 2.9924. Min Range: -2.9924

Max Act: 2.4033. Min Act: -0.0000

Data Index: 420789 (C4 (Web Text))

Max Activating Token Index: 53

Text #6

Max Range: 2.9924. Min Range: -2.9924

Max Act: 2.3730. Min Act: -0.0000

Data Index: 830481 (C4 (Web Text))

Max Activating Token Index: 149

Text #7

Max Range: 2.9924. Min Range: -2.9924

Max Act: 1.9972. Min Act: -0.0000

Data Index: 1114009 (C4 (Web Text))

Max Activating Token Index: 276

Text #8

Max Range: 2.9924. Min Range: -2.9924

Max Act: 2.2199. Min Act: -0.0000

Data Index: 1095571 (C4 (Web Text))

Max Activating Token Index: 101

Text #9

Max Range: 2.9924. Min Range: -2.9924

Max Act: 2.1891. Min Act: -0.0000

Data Index: 1232651 (C4 (Web Text))

Max Activating Token Index: 871

Text #10

Max Range: 2.9924. Min Range: -2.9924

Max Act: 2.0643. Min Act: -0.0000

Data Index: 692361 (C4 (Web Text))

Max Activating Token Index: 745

Text #11

Max Range: 2.9924. Min Range: -2.9924

Max Act: 2.1667. Min Act: -0.0000

Data Index: 1205480 (C4 (Web Text))

Max Activating Token Index: 881

Text #12

Max Range: 2.9924. Min Range: -2.9924

Max Act: 2.2524. Min Act: -0.0000

Data Index: 926423 (C4 (Web Text))

Max Activating Token Index: 8

Text #13

Max Range: 2.9924. Min Range: -2.9924

Max Act: 2.1362. Min Act: -0.0000

Data Index: 680340 (C4 (Web Text))

Max Activating Token Index: 278

Text #14

Max Range: 2.9924. Min Range: -2.9924

Max Act: 2.2209. Min Act: -0.0000

Data Index: 132862 (C4 (Web Text))

Max Activating Token Index: 942

Text #15

Max Range: 2.9924. Min Range: -2.9924

Max Act: 2.3236. Min Act: -0.0000

Data Index: 793002 (C4 (Web Text))

Max Activating Token Index: 106

Text #16

Max Range: 2.9924. Min Range: -2.9924

Max Act: 2.2263. Min Act: -0.0000

Data Index: 1062266 (C4 (Web Text))

Max Activating Token Index: 747

Text #17

Max Range: 2.9924. Min Range: -2.9924

Max Act: 2.2158. Min Act: -0.0000

Data Index: 85439 (C4 (Web Text))

Max Activating Token Index: 650

Text #18

Max Range: 2.9924. Min Range: -2.9924

Max Act: 1.9535. Min Act: -0.0000

Data Index: 795669 (C4 (Web Text))

Max Activating Token Index: 707

Text #19

Max Range: 2.9924. Min Range: -2.9924

Max Act: 2.1354. Min Act: -0.0000

Data Index: 1355676 (C4 (Web Text))

Max Activating Token Index: 118