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

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

Neuron 2919 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2650. Min Range: -1.2650

Max Act: 1.2650. Min Act: -0.0003

Data Index: 1231122 (C4 (Web Text))

Max Activating Token Index: 561

Text #1

Max Range: 1.2650. Min Range: -1.2650

Max Act: 1.1410. Min Act: -0.0003

Data Index: 1022035 (C4 (Web Text))

Max Activating Token Index: 483

Text #2

Max Range: 1.2650. Min Range: -1.2650

Max Act: 1.0714. Min Act: -0.0003

Data Index: 670033 (C4 (Web Text))

Max Activating Token Index: 184

Text #3

Max Range: 1.2650. Min Range: -1.2650

Max Act: 1.0396. Min Act: -0.0003

Data Index: 371065 (C4 (Web Text))

Max Activating Token Index: 499

Text #4

Max Range: 1.2650. Min Range: -1.2650

Max Act: 1.0204. Min Act: -0.0003

Data Index: 141874 (C4 (Web Text))

Max Activating Token Index: 779

Text #5

Max Range: 1.2650. Min Range: -1.2650

Max Act: 0.9827. Min Act: -0.0002

Data Index: 572697 (C4 (Web Text))

Max Activating Token Index: 41

Text #6

Max Range: 1.2650. Min Range: -1.2650

Max Act: 0.9813. Min Act: -0.0003

Data Index: 1225026 (C4 (Web Text))

Max Activating Token Index: 98

Text #7

Max Range: 1.2650. Min Range: -1.2650

Max Act: 1.0030. Min Act: -0.0003

Data Index: 639577 (C4 (Web Text))

Max Activating Token Index: 965

Text #8

Max Range: 1.2650. Min Range: -1.2650

Max Act: 0.9660. Min Act: -0.0003

Data Index: 880185 (C4 (Web Text))

Max Activating Token Index: 938

Text #9

Max Range: 1.2650. Min Range: -1.2650

Max Act: 1.0155. Min Act: -0.0003

Data Index: 1305375 (C4 (Web Text))

Max Activating Token Index: 953

Text #10

Max Range: 1.2650. Min Range: -1.2650

Max Act: 0.9484. Min Act: -0.0003

Data Index: 902604 (C4 (Web Text))

Max Activating Token Index: 430

Text #11

Max Range: 1.2650. Min Range: -1.2650

Max Act: 0.9886. Min Act: -0.0003

Data Index: 19502 (C4 (Web Text))

Max Activating Token Index: 153

Text #12

Max Range: 1.2650. Min Range: -1.2650

Max Act: 0.9137. Min Act: -0.0002

Data Index: 216084 (C4 (Web Text))

Max Activating Token Index: 1001

Text #13

Max Range: 1.2650. Min Range: -1.2650

Max Act: 0.8952. Min Act: -0.0003

Data Index: 686815 (C4 (Web Text))

Max Activating Token Index: 173

Text #14

Max Range: 1.2650. Min Range: -1.2650

Max Act: 0.8694. Min Act: -0.0003

Data Index: 548038 (C4 (Web Text))

Max Activating Token Index: 748

Text #15

Max Range: 1.2650. Min Range: -1.2650

Max Act: 0.9157. Min Act: -0.0003

Data Index: 2564 (C4 (Web Text))

Max Activating Token Index: 420

Text #16

Max Range: 1.2650. Min Range: -1.2650

Max Act: 0.9122. Min Act: -0.0003

Data Index: 743030 (C4 (Web Text))

Max Activating Token Index: 314

Text #17

Max Range: 1.2650. Min Range: -1.2650

Max Act: 0.9138. Min Act: -0.0003

Data Index: 463975 (C4 (Web Text))

Max Activating Token Index: 344

Text #18

Max Range: 1.2650. Min Range: -1.2650

Max Act: 0.8767. Min Act: -0.0003

Data Index: 294259 (C4 (Web Text))

Max Activating Token Index: 73

Text #19

Max Range: 1.2650. Min Range: -1.2650

Max Act: 0.8436. Min Act: -0.0003

Data Index: 1105563 (C4 (Web Text))

Max Activating Token Index: 641