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

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

Neuron 909 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 15.5880. Min Range: -15.5880

Max Act: 15.5880. Min Act: -0.0000

Data Index: 354192 (C4 (Web Text))

Max Activating Token Index: 833

Text #1

Max Range: 15.5880. Min Range: -15.5880

Max Act: 9.2316. Min Act: -0.0000

Data Index: 262866 (C4 (Web Text))

Max Activating Token Index: 566

Text #2

Max Range: 15.5880. Min Range: -15.5880

Max Act: 9.8931. Min Act: -0.0000

Data Index: 377521 (C4 (Web Text))

Max Activating Token Index: 376

Text #3

Max Range: 15.5880. Min Range: -15.5880

Max Act: 10.9182. Min Act: -0.0000

Data Index: 1277797 (C4 (Web Text))

Max Activating Token Index: 309

Text #4

Max Range: 15.5880. Min Range: -15.5880

Max Act: 5.1936. Min Act: -0.0000

Data Index: 1351275 (C4 (Web Text))

Max Activating Token Index: 965

Text #5

Max Range: 15.5880. Min Range: -15.5880

Max Act: 4.3102. Min Act: -0.0000

Data Index: 90744 (C4 (Web Text))

Max Activating Token Index: 26

Text #6

Max Range: 15.5880. Min Range: -15.5880

Max Act: 7.9796. Min Act: -0.0000

Data Index: 343977 (C4 (Web Text))

Max Activating Token Index: 532

Text #7

Max Range: 15.5880. Min Range: -15.5880

Max Act: 0.6817. Min Act: -0.0000

Data Index: 714416 (C4 (Web Text))

Max Activating Token Index: 933

Text #8

Max Range: 15.5880. Min Range: -15.5880

Max Act: 1.6209. Min Act: -0.0000

Data Index: 724151 (C4 (Web Text))

Max Activating Token Index: 331

Text #9

Max Range: 15.5880. Min Range: -15.5880

Max Act: 1.2326. Min Act: 0.0000

Data Index: 786282 (C4 (Web Text))

Max Activating Token Index: 890

Text #10

Max Range: 15.5880. Min Range: -15.5880

Max Act: 1.3263. Min Act: -0.0000

Data Index: 203538 (C4 (Web Text))

Max Activating Token Index: 70

Text #11

Max Range: 15.5880. Min Range: -15.5880

Max Act: 0.2938. Min Act: -0.0000

Data Index: 200772 (C4 (Web Text))

Max Activating Token Index: 636

Text #12

Max Range: 15.5880. Min Range: -15.5880

Max Act: 3.9827. Min Act: -0.0000

Data Index: 1137894 (C4 (Web Text))

Max Activating Token Index: 954

Text #13

Max Range: 15.5880. Min Range: -15.5880

Max Act: 1.7380. Min Act: -0.0000

Data Index: 878109 (C4 (Web Text))

Max Activating Token Index: 84

Text #14

Max Range: 15.5880. Min Range: -15.5880

Max Act: 0.2763. Min Act: -0.0000

Data Index: 1048403 (C4 (Web Text))

Max Activating Token Index: 310

Text #15

Max Range: 15.5880. Min Range: -15.5880

Max Act: 1.0276. Min Act: -0.0000

Data Index: 1034574 (C4 (Web Text))

Max Activating Token Index: 427

Text #16

Max Range: 15.5880. Min Range: -15.5880

Max Act: 0.1803. Min Act: -0.0000

Data Index: 592830 (C4 (Web Text))

Max Activating Token Index: 535

Text #17

Max Range: 15.5880. Min Range: -15.5880

Max Act: 0.5042. Min Act: -0.0000

Data Index: 1214733 (C4 (Web Text))

Max Activating Token Index: 227

Text #18

Max Range: 15.5880. Min Range: -15.5880

Max Act: 0.3793. Min Act: -0.0000

Data Index: 631964 (C4 (Web Text))

Max Activating Token Index: 41

Text #19

Max Range: 15.5880. Min Range: -15.5880

Max Act: 0.5579. Min Act: -0.0000

Data Index: 1125878 (C4 (Web Text))

Max Activating Token Index: 27