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

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

Neuron 1515 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.1297. Min Act: -0.0000

Data Index: 359412 (C4 (Web Text))

Max Activating Token Index: 995

Text #1

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.1256. Min Act: -0.0000

Data Index: 520599 (C4 (Web Text))

Max Activating Token Index: 570

Text #2

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.1063. Min Act: -0.0000

Data Index: 667862 (C4 (Web Text))

Max Activating Token Index: 306

Text #3

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.1154. Min Act: -0.0000

Data Index: 871901 (C4 (Web Text))

Max Activating Token Index: 256

Text #4

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.1072. Min Act: -0.0000

Data Index: 1300019 (C4 (Web Text))

Max Activating Token Index: 829

Text #5

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.1005. Min Act: -0.0000

Data Index: 1176906 (C4 (Web Text))

Max Activating Token Index: 454

Text #6

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.1033. Min Act: -0.0000

Data Index: 503695 (C4 (Web Text))

Max Activating Token Index: 105

Text #7

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.0998. Min Act: -0.0000

Data Index: 1625136 (Python Code)

Max Activating Token Index: 46

Text #8

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.0986. Min Act: -0.0000

Data Index: 1024736 (C4 (Web Text))

Max Activating Token Index: 964

Text #9

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.0989. Min Act: -0.0000

Data Index: 1221377 (C4 (Web Text))

Max Activating Token Index: 284

Text #10

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.0917. Min Act: -0.0000

Data Index: 465883 (C4 (Web Text))

Max Activating Token Index: 198

Text #11

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.0944. Min Act: -0.0000

Data Index: 491727 (C4 (Web Text))

Max Activating Token Index: 895

Text #12

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.0970. Min Act: -0.0000

Data Index: 761130 (C4 (Web Text))

Max Activating Token Index: 6

Text #13

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.1028. Min Act: -0.0000

Data Index: 481811 (C4 (Web Text))

Max Activating Token Index: 831

Text #14

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.0927. Min Act: -0.0000

Data Index: 1536914 (Python Code)

Max Activating Token Index: 833

Text #15

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.0891. Min Act: -0.0000

Data Index: 876613 (C4 (Web Text))

Max Activating Token Index: 631

Text #16

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.0815. Min Act: -0.0000

Data Index: 296297 (C4 (Web Text))

Max Activating Token Index: 450

Text #17

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.0817. Min Act: -0.0000

Data Index: 325117 (C4 (Web Text))

Max Activating Token Index: 486

Text #18

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.0851. Min Act: -0.0000

Data Index: 872678 (C4 (Web Text))

Max Activating Token Index: 169

Text #19

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.0821. Min Act: -0.0000

Data Index: 851382 (C4 (Web Text))

Max Activating Token Index: 133