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

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

Neuron 501 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: 0.1417. Min Range: -0.1417

Max Act: 0.1417. Min Act: -0.0003

Data Index: 966545 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.1417. Min Range: -0.1417

Max Act: 0.1371. Min Act: -0.0003

Data Index: 562533 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.1417. Min Range: -0.1417

Max Act: 0.1318. Min Act: -0.0003

Data Index: 424806 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.1417. Min Range: -0.1417

Max Act: 0.1234. Min Act: -0.0003

Data Index: 13742 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.1417. Min Range: -0.1417

Max Act: 0.1021. Min Act: -0.0003

Data Index: 536727 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.1417. Min Range: -0.1417

Max Act: 0.1167. Min Act: -0.0003

Data Index: 1346108 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.1417. Min Range: -0.1417

Max Act: 0.1224. Min Act: -0.0003

Data Index: 805549 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.1417. Min Range: -0.1417

Max Act: 0.1191. Min Act: -0.0003

Data Index: 416424 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.1417. Min Range: -0.1417

Max Act: 0.1246. Min Act: -0.0003

Data Index: 270509 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.1417. Min Range: -0.1417

Max Act: 0.1200. Min Act: -0.0003

Data Index: 1124451 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.1417. Min Range: -0.1417

Max Act: 0.1072. Min Act: -0.0003

Data Index: 1252507 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.1417. Min Range: -0.1417

Max Act: 0.0952. Min Act: -0.0003

Data Index: 597656 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.1417. Min Range: -0.1417

Max Act: 0.1133. Min Act: -0.0003

Data Index: 121677 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.1417. Min Range: -0.1417

Max Act: 0.0744. Min Act: -0.0003

Data Index: 1027049 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.1417. Min Range: -0.1417

Max Act: 0.1082. Min Act: -0.0003

Data Index: 486014 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.1417. Min Range: -0.1417

Max Act: 0.0983. Min Act: -0.0003

Data Index: 909652 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.1417. Min Range: -0.1417

Max Act: 0.1008. Min Act: -0.0003

Data Index: 572146 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.1417. Min Range: -0.1417

Max Act: 0.1071. Min Act: -0.0003

Data Index: 1072082 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.1417. Min Range: -0.1417

Max Act: 0.1070. Min Act: -0.0003

Data Index: 928002 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.1417. Min Range: -0.1417

Max Act: 0.1007. Min Act: -0.0003

Data Index: 1475068 (Python Code)

Max Activating Token Index: 1023