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

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

Neuron 1938 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.1088. Min Act: -0.0001

Data Index: 832111 (C4 (Web Text))

Max Activating Token Index: 975

Text #1

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.0896. Min Act: -0.0001

Data Index: 726975 (C4 (Web Text))

Max Activating Token Index: 829

Text #2

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.1010. Min Act: -0.0001

Data Index: 694398 (C4 (Web Text))

Max Activating Token Index: 233

Text #3

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.1002. Min Act: -0.0001

Data Index: 391989 (C4 (Web Text))

Max Activating Token Index: 964

Text #4

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.1009. Min Act: -0.0001

Data Index: 721813 (C4 (Web Text))

Max Activating Token Index: 88

Text #5

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.0941. Min Act: -0.0001

Data Index: 255495 (C4 (Web Text))

Max Activating Token Index: 701

Text #6

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.1024. Min Act: -0.0001

Data Index: 804248 (C4 (Web Text))

Max Activating Token Index: 287

Text #7

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.0920. Min Act: -0.0001

Data Index: 636187 (C4 (Web Text))

Max Activating Token Index: 742

Text #8

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.0914. Min Act: -0.0001

Data Index: 1642619 (Python Code)

Max Activating Token Index: 267

Text #9

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.0816. Min Act: -0.0001

Data Index: 1142990 (C4 (Web Text))

Max Activating Token Index: 294

Text #10

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.0906. Min Act: -0.0001

Data Index: 1175008 (C4 (Web Text))

Max Activating Token Index: 558

Text #11

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.0941. Min Act: -0.0001

Data Index: 1268126 (C4 (Web Text))

Max Activating Token Index: 887

Text #12

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.0888. Min Act: -0.0001

Data Index: 1311227 (C4 (Web Text))

Max Activating Token Index: 580

Text #13

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.0956. Min Act: -0.0001

Data Index: 1295051 (C4 (Web Text))

Max Activating Token Index: 562

Text #14

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.0884. Min Act: -0.0001

Data Index: 1231831 (C4 (Web Text))

Max Activating Token Index: 289

Text #15

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.0906. Min Act: -0.0001

Data Index: 796205 (C4 (Web Text))

Max Activating Token Index: 829

Text #16

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.0876. Min Act: -0.0001

Data Index: 1164922 (C4 (Web Text))

Max Activating Token Index: 935

Text #17

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.0831. Min Act: -0.0001

Data Index: 1217040 (C4 (Web Text))

Max Activating Token Index: 715

Text #18

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.0897. Min Act: -0.0001

Data Index: 1255840 (C4 (Web Text))

Max Activating Token Index: 600

Text #19

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.0855. Min Act: -0.0001

Data Index: 918041 (C4 (Web Text))

Max Activating Token Index: 112