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

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

Neuron 5186 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 2.1150. Min Range: -2.1150

Max Act: 2.1150. Min Act: -0.0002

Data Index: 287889 (C4 (Web Text))

Max Activating Token Index: 29

Text #1

Max Range: 2.1150. Min Range: -2.1150

Max Act: 2.0188. Min Act: -0.0002

Data Index: 1120494 (C4 (Web Text))

Max Activating Token Index: 31

Text #2

Max Range: 2.1150. Min Range: -2.1150

Max Act: 1.9142. Min Act: -0.0002

Data Index: 876877 (C4 (Web Text))

Max Activating Token Index: 15

Text #3

Max Range: 2.1150. Min Range: -2.1150

Max Act: 1.8822. Min Act: -0.0002

Data Index: 704644 (C4 (Web Text))

Max Activating Token Index: 778

Text #4

Max Range: 2.1150. Min Range: -2.1150

Max Act: 1.8678. Min Act: -0.0002

Data Index: 831827 (C4 (Web Text))

Max Activating Token Index: 151

Text #5

Max Range: 2.1150. Min Range: -2.1150

Max Act: 1.9151. Min Act: -0.0002

Data Index: 16112 (C4 (Web Text))

Max Activating Token Index: 871

Text #6

Max Range: 2.1150. Min Range: -2.1150

Max Act: 1.9043. Min Act: -0.0002

Data Index: 283196 (C4 (Web Text))

Max Activating Token Index: 708

Text #7

Max Range: 2.1150. Min Range: -2.1150

Max Act: 1.8675. Min Act: -0.0002

Data Index: 1163228 (C4 (Web Text))

Max Activating Token Index: 846

Text #8

Max Range: 2.1150. Min Range: -2.1150

Max Act: 1.8347. Min Act: -0.0002

Data Index: 980404 (C4 (Web Text))

Max Activating Token Index: 259

Text #9

Max Range: 2.1150. Min Range: -2.1150

Max Act: 1.8096. Min Act: -0.0002

Data Index: 72428 (C4 (Web Text))

Max Activating Token Index: 710

Text #10

Max Range: 2.1150. Min Range: -2.1150

Max Act: 1.8421. Min Act: -0.0002

Data Index: 707215 (C4 (Web Text))

Max Activating Token Index: 686

Text #11

Max Range: 2.1150. Min Range: -2.1150

Max Act: 1.7489. Min Act: -0.0002

Data Index: 1032434 (C4 (Web Text))

Max Activating Token Index: 31

Text #12

Max Range: 2.1150. Min Range: -2.1150

Max Act: 1.7343. Min Act: -0.0002

Data Index: 1072153 (C4 (Web Text))

Max Activating Token Index: 926

Text #13

Max Range: 2.1150. Min Range: -2.1150

Max Act: 1.7204. Min Act: -0.0002

Data Index: 1216012 (C4 (Web Text))

Max Activating Token Index: 793

Text #14

Max Range: 2.1150. Min Range: -2.1150

Max Act: 1.6731. Min Act: -0.0002

Data Index: 599067 (C4 (Web Text))

Max Activating Token Index: 57

Text #15

Max Range: 2.1150. Min Range: -2.1150

Max Act: 1.6662. Min Act: -0.0002

Data Index: 388759 (C4 (Web Text))

Max Activating Token Index: 30

Text #16

Max Range: 2.1150. Min Range: -2.1150

Max Act: 1.6907. Min Act: -0.0002

Data Index: 441664 (C4 (Web Text))

Max Activating Token Index: 16

Text #17

Max Range: 2.1150. Min Range: -2.1150

Max Act: 1.6845. Min Act: -0.0002

Data Index: 887545 (C4 (Web Text))

Max Activating Token Index: 758

Text #18

Max Range: 2.1150. Min Range: -2.1150

Max Act: 1.6581. Min Act: -0.0002

Data Index: 1052779 (C4 (Web Text))

Max Activating Token Index: 843

Text #19

Max Range: 2.1150. Min Range: -2.1150

Max Act: 1.6369. Min Act: -0.0002

Data Index: 47000 (C4 (Web Text))

Max Activating Token Index: 935