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

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

Neuron 4855 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6069. Min Range: -0.6069

Max Act: 0.6069. Min Act: -0.0000

Data Index: 489666 (C4 (Web Text))

Max Activating Token Index: 367

Text #1

Max Range: 0.6069. Min Range: -0.6069

Max Act: 0.5970. Min Act: -0.0000

Data Index: 570556 (C4 (Web Text))

Max Activating Token Index: 396

Text #2

Max Range: 0.6069. Min Range: -0.6069

Max Act: 0.5890. Min Act: -0.0000

Data Index: 95510 (C4 (Web Text))

Max Activating Token Index: 926

Text #3

Max Range: 0.6069. Min Range: -0.6069

Max Act: 0.5855. Min Act: -0.0000

Data Index: 324702 (C4 (Web Text))

Max Activating Token Index: 335

Text #4

Max Range: 0.6069. Min Range: -0.6069

Max Act: 0.5747. Min Act: -0.0000

Data Index: 440318 (C4 (Web Text))

Max Activating Token Index: 978

Text #5

Max Range: 0.6069. Min Range: -0.6069

Max Act: 0.5419. Min Act: -0.0000

Data Index: 1303691 (C4 (Web Text))

Max Activating Token Index: 686

Text #6

Max Range: 0.6069. Min Range: -0.6069

Max Act: 0.5386. Min Act: -0.0000

Data Index: 1631895 (Python Code)

Max Activating Token Index: 46

Text #7

Max Range: 0.6069. Min Range: -0.6069

Max Act: 0.5238. Min Act: -0.0000

Data Index: 1500052 (Python Code)

Max Activating Token Index: 517

Text #8

Max Range: 0.6069. Min Range: -0.6069

Max Act: 0.5575. Min Act: -0.0000

Data Index: 92381 (C4 (Web Text))

Max Activating Token Index: 147

Text #9

Max Range: 0.6069. Min Range: -0.6069

Max Act: 0.5861. Min Act: -0.0000

Data Index: 99919 (C4 (Web Text))

Max Activating Token Index: 722

Text #10

Max Range: 0.6069. Min Range: -0.6069

Max Act: 0.5145. Min Act: -0.0000

Data Index: 1574595 (Python Code)

Max Activating Token Index: 238

Text #11

Max Range: 0.6069. Min Range: -0.6069

Max Act: 0.5046. Min Act: -0.0000

Data Index: 1495282 (Python Code)

Max Activating Token Index: 505

Text #12

Max Range: 0.6069. Min Range: -0.6069

Max Act: 0.5151. Min Act: -0.0000

Data Index: 263479 (C4 (Web Text))

Max Activating Token Index: 154

Text #13

Max Range: 0.6069. Min Range: -0.6069

Max Act: 0.4962. Min Act: -0.0000

Data Index: 1616526 (Python Code)

Max Activating Token Index: 924

Text #14

Max Range: 0.6069. Min Range: -0.6069

Max Act: 0.5091. Min Act: -0.0000

Data Index: 1387705 (Python Code)

Max Activating Token Index: 732

Text #15

Max Range: 0.6069. Min Range: -0.6069

Max Act: 0.5032. Min Act: -0.0000

Data Index: 1369110 (Python Code)

Max Activating Token Index: 41

Text #16

Max Range: 0.6069. Min Range: -0.6069

Max Act: 0.5026. Min Act: -0.0000

Data Index: 259467 (C4 (Web Text))

Max Activating Token Index: 273

Text #17

Max Range: 0.6069. Min Range: -0.6069

Max Act: 0.4941. Min Act: -0.0000

Data Index: 1647121 (Python Code)

Max Activating Token Index: 114

Text #18

Max Range: 0.6069. Min Range: -0.6069

Max Act: 0.5059. Min Act: -0.0000

Data Index: 1564702 (Python Code)

Max Activating Token Index: 177

Text #19

Max Range: 0.6069. Min Range: -0.6069

Max Act: 0.4735. Min Act: -0.0000

Data Index: 1379681 (Python Code)

Max Activating Token Index: 16