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

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

Neuron 3682 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: 1.5030. Min Range: -1.5030

Max Act: 1.5030. Min Act: -0.0000

Data Index: 690447 (C4 (Web Text))

Max Activating Token Index: 860

Text #1

Max Range: 1.5030. Min Range: -1.5030

Max Act: 1.4861. Min Act: -0.0000

Data Index: 806831 (C4 (Web Text))

Max Activating Token Index: 230

Text #2

Max Range: 1.5030. Min Range: -1.5030

Max Act: 1.2901. Min Act: -0.0000

Data Index: 615332 (C4 (Web Text))

Max Activating Token Index: 644

Text #3

Max Range: 1.5030. Min Range: -1.5030

Max Act: 1.2739. Min Act: 0.0000

Data Index: 1015477 (C4 (Web Text))

Max Activating Token Index: 90

Text #4

Max Range: 1.5030. Min Range: -1.5030

Max Act: 1.1175. Min Act: -0.0000

Data Index: 670536 (C4 (Web Text))

Max Activating Token Index: 819

Text #5

Max Range: 1.5030. Min Range: -1.5030

Max Act: 1.1450. Min Act: -0.0000

Data Index: 715171 (C4 (Web Text))

Max Activating Token Index: 215

Text #6

Max Range: 1.5030. Min Range: -1.5030

Max Act: 1.1071. Min Act: -0.0000

Data Index: 370739 (C4 (Web Text))

Max Activating Token Index: 80

Text #7

Max Range: 1.5030. Min Range: -1.5030

Max Act: 1.0939. Min Act: -0.0000

Data Index: 167818 (C4 (Web Text))

Max Activating Token Index: 842

Text #8

Max Range: 1.5030. Min Range: -1.5030

Max Act: 1.0950. Min Act: -0.0000

Data Index: 894288 (C4 (Web Text))

Max Activating Token Index: 881

Text #9

Max Range: 1.5030. Min Range: -1.5030

Max Act: 1.0241. Min Act: -0.0000

Data Index: 1162253 (C4 (Web Text))

Max Activating Token Index: 885

Text #10

Max Range: 1.5030. Min Range: -1.5030

Max Act: 1.0735. Min Act: -0.0000

Data Index: 1290912 (C4 (Web Text))

Max Activating Token Index: 950

Text #11

Max Range: 1.5030. Min Range: -1.5030

Max Act: 1.0535. Min Act: -0.0000

Data Index: 497983 (C4 (Web Text))

Max Activating Token Index: 466

Text #12

Max Range: 1.5030. Min Range: -1.5030

Max Act: 1.0713. Min Act: -0.0000

Data Index: 180432 (C4 (Web Text))

Max Activating Token Index: 7

Text #13

Max Range: 1.5030. Min Range: -1.5030

Max Act: 1.0039. Min Act: -0.0000

Data Index: 748780 (C4 (Web Text))

Max Activating Token Index: 459

Text #14

Max Range: 1.5030. Min Range: -1.5030

Max Act: 1.1245. Min Act: -0.0000

Data Index: 755256 (C4 (Web Text))

Max Activating Token Index: 89

Text #15

Max Range: 1.5030. Min Range: -1.5030

Max Act: 1.1224. Min Act: -0.0000

Data Index: 356412 (C4 (Web Text))

Max Activating Token Index: 546

Text #16

Max Range: 1.5030. Min Range: -1.5030

Max Act: 1.0345. Min Act: -0.0000

Data Index: 1356526 (C4 (Web Text))

Max Activating Token Index: 754

Text #17

Max Range: 1.5030. Min Range: -1.5030

Max Act: 1.0294. Min Act: -0.0000

Data Index: 1209176 (C4 (Web Text))

Max Activating Token Index: 43

Text #18

Max Range: 1.5030. Min Range: -1.5030

Max Act: 1.0162. Min Act: -0.0000

Data Index: 920888 (C4 (Web Text))

Max Activating Token Index: 467

Text #19

Max Range: 1.5030. Min Range: -1.5030

Max Act: 1.0030. Min Act: -0.0000

Data Index: 1004138 (C4 (Web Text))

Max Activating Token Index: 855