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

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

Neuron 3053 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: 2.1504. Min Range: -2.1504

Max Act: 1.7360. Min Act: -0.0000

Data Index: 701654 (C4 (Web Text))

Max Activating Token Index: 58

Text #1

Max Range: 2.1504. Min Range: -2.1504

Max Act: 2.1504. Min Act: -0.0000

Data Index: 169515 (C4 (Web Text))

Max Activating Token Index: 154

Text #2

Max Range: 2.1504. Min Range: -2.1504

Max Act: 1.7024. Min Act: -0.0000

Data Index: 1076506 (C4 (Web Text))

Max Activating Token Index: 967

Text #3

Max Range: 2.1504. Min Range: -2.1504

Max Act: 1.8028. Min Act: -0.0000

Data Index: 97149 (C4 (Web Text))

Max Activating Token Index: 352

Text #4

Max Range: 2.1504. Min Range: -2.1504

Max Act: 1.7791. Min Act: -0.0000

Data Index: 579551 (C4 (Web Text))

Max Activating Token Index: 807

Text #5

Max Range: 2.1504. Min Range: -2.1504

Max Act: 1.6086. Min Act: -0.0000

Data Index: 1063007 (C4 (Web Text))

Max Activating Token Index: 13

Text #6

Max Range: 2.1504. Min Range: -2.1504

Max Act: 1.5185. Min Act: -0.0001

Data Index: 975663 (C4 (Web Text))

Max Activating Token Index: 267

Text #7

Max Range: 2.1504. Min Range: -2.1504

Max Act: 1.6000. Min Act: -0.0000

Data Index: 321825 (C4 (Web Text))

Max Activating Token Index: 19

Text #8

Max Range: 2.1504. Min Range: -2.1504

Max Act: 1.8043. Min Act: -0.0000

Data Index: 576161 (C4 (Web Text))

Max Activating Token Index: 628

Text #9

Max Range: 2.1504. Min Range: -2.1504

Max Act: 1.5225. Min Act: -0.0000

Data Index: 1029286 (C4 (Web Text))

Max Activating Token Index: 673

Text #10

Max Range: 2.1504. Min Range: -2.1504

Max Act: 1.3509. Min Act: -0.0000

Data Index: 847890 (C4 (Web Text))

Max Activating Token Index: 996

Text #11

Max Range: 2.1504. Min Range: -2.1504

Max Act: 1.4754. Min Act: -0.0000

Data Index: 887966 (C4 (Web Text))

Max Activating Token Index: 993

Text #12

Max Range: 2.1504. Min Range: -2.1504

Max Act: 1.0741. Min Act: -0.0000

Data Index: 676717 (C4 (Web Text))

Max Activating Token Index: 234

Text #13

Max Range: 2.1504. Min Range: -2.1504

Max Act: 1.4748. Min Act: -0.0000

Data Index: 708738 (C4 (Web Text))

Max Activating Token Index: 461

Text #14

Max Range: 2.1504. Min Range: -2.1504

Max Act: 1.4674. Min Act: -0.0000

Data Index: 302183 (C4 (Web Text))

Max Activating Token Index: 866

Text #15

Max Range: 2.1504. Min Range: -2.1504

Max Act: 1.3755. Min Act: -0.0000

Data Index: 862084 (C4 (Web Text))

Max Activating Token Index: 1013

Text #16

Max Range: 2.1504. Min Range: -2.1504

Max Act: 1.3699. Min Act: -0.0000

Data Index: 776024 (C4 (Web Text))

Max Activating Token Index: 392

Text #17

Max Range: 2.1504. Min Range: -2.1504

Max Act: 1.4292. Min Act: -0.0000

Data Index: 698970 (C4 (Web Text))

Max Activating Token Index: 480

Text #18

Max Range: 2.1504. Min Range: -2.1504

Max Act: 1.4888. Min Act: -0.0000

Data Index: 710564 (C4 (Web Text))

Max Activating Token Index: 488

Text #19

Max Range: 2.1504. Min Range: -2.1504

Max Act: 1.5960. Min Act: -0.0000

Data Index: 259488 (C4 (Web Text))

Max Activating Token Index: 742