Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1662 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0878. Min Act: -0.0003

Data Index: 777050 (C4 (Web Text))

Max Activating Token Index: 556

Text #1

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0854. Min Act: -0.0003

Data Index: 1314489 (C4 (Web Text))

Max Activating Token Index: 584

Text #2

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0846. Min Act: -0.0003

Data Index: 1145066 (C4 (Web Text))

Max Activating Token Index: 117

Text #3

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0802. Min Act: -0.0003

Data Index: 331968 (C4 (Web Text))

Max Activating Token Index: 190

Text #4

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0636. Min Act: -0.0003

Data Index: 1332294 (C4 (Web Text))

Max Activating Token Index: 630

Text #5

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0779. Min Act: -0.0003

Data Index: 666956 (C4 (Web Text))

Max Activating Token Index: 93

Text #6

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0791. Min Act: -0.0003

Data Index: 270127 (C4 (Web Text))

Max Activating Token Index: 242

Text #7

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0669. Min Act: -0.0003

Data Index: 265977 (C4 (Web Text))

Max Activating Token Index: 623

Text #8

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0638. Min Act: -0.0003

Data Index: 831428 (C4 (Web Text))

Max Activating Token Index: 200

Text #9

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0610. Min Act: -0.0003

Data Index: 807612 (C4 (Web Text))

Max Activating Token Index: 575

Text #10

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0645. Min Act: -0.0003

Data Index: 932039 (C4 (Web Text))

Max Activating Token Index: 37

Text #11

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0696. Min Act: -0.0003

Data Index: 613191 (C4 (Web Text))

Max Activating Token Index: 302

Text #12

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0660. Min Act: -0.0003

Data Index: 853999 (C4 (Web Text))

Max Activating Token Index: 149

Text #13

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0668. Min Act: -0.0003

Data Index: 466842 (C4 (Web Text))

Max Activating Token Index: 908

Text #14

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0687. Min Act: -0.0003

Data Index: 1404824 (Python Code)

Max Activating Token Index: 225

Text #15

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0637. Min Act: -0.0003

Data Index: 1208817 (C4 (Web Text))

Max Activating Token Index: 199

Text #16

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0609. Min Act: -0.0003

Data Index: 478950 (C4 (Web Text))

Max Activating Token Index: 756

Text #17

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0603. Min Act: -0.0003

Data Index: 1148190 (C4 (Web Text))

Max Activating Token Index: 845

Text #18

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0579. Min Act: -0.0003

Data Index: 534268 (C4 (Web Text))

Max Activating Token Index: 256

Text #19

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0617. Min Act: -0.0003

Data Index: 32386 (C4 (Web Text))

Max Activating Token Index: 777