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

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

Neuron 1509 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: 5.1193. Min Range: -5.1193

Max Act: 5.1193. Min Act: -0.0001

Data Index: 29819 (C4 (Web Text))

Max Activating Token Index: 590

Text #1

Max Range: 5.1193. Min Range: -5.1193

Max Act: 4.0782. Min Act: -0.0001

Data Index: 851970 (C4 (Web Text))

Max Activating Token Index: 791

Text #2

Max Range: 5.1193. Min Range: -5.1193

Max Act: 3.8043. Min Act: -0.0001

Data Index: 828644 (C4 (Web Text))

Max Activating Token Index: 868

Text #3

Max Range: 5.1193. Min Range: -5.1193

Max Act: 3.0083. Min Act: -0.0001

Data Index: 238333 (C4 (Web Text))

Max Activating Token Index: 96

Text #4

Max Range: 5.1193. Min Range: -5.1193

Max Act: 3.1068. Min Act: -0.0001

Data Index: 888643 (C4 (Web Text))

Max Activating Token Index: 820

Text #5

Max Range: 5.1193. Min Range: -5.1193

Max Act: 3.1047. Min Act: -0.0001

Data Index: 563485 (C4 (Web Text))

Max Activating Token Index: 337

Text #6

Max Range: 5.1193. Min Range: -5.1193

Max Act: 2.8862. Min Act: -0.0001

Data Index: 952348 (C4 (Web Text))

Max Activating Token Index: 1021

Text #7

Max Range: 5.1193. Min Range: -5.1193

Max Act: 2.5112. Min Act: -0.0001

Data Index: 297472 (C4 (Web Text))

Max Activating Token Index: 866

Text #8

Max Range: 5.1193. Min Range: -5.1193

Max Act: 2.3457. Min Act: -0.0001

Data Index: 1297313 (C4 (Web Text))

Max Activating Token Index: 114

Text #9

Max Range: 5.1193. Min Range: -5.1193

Max Act: 2.5378. Min Act: -0.0001

Data Index: 490612 (C4 (Web Text))

Max Activating Token Index: 308

Text #10

Max Range: 5.1193. Min Range: -5.1193

Max Act: 2.2936. Min Act: -0.0001

Data Index: 716557 (C4 (Web Text))

Max Activating Token Index: 228

Text #11

Max Range: 5.1193. Min Range: -5.1193

Max Act: 2.0913. Min Act: -0.0001

Data Index: 623081 (C4 (Web Text))

Max Activating Token Index: 356

Text #12

Max Range: 5.1193. Min Range: -5.1193

Max Act: 2.3189. Min Act: -0.0001

Data Index: 1319318 (C4 (Web Text))

Max Activating Token Index: 594

Text #13

Max Range: 5.1193. Min Range: -5.1193

Max Act: 2.4335. Min Act: -0.0001

Data Index: 981049 (C4 (Web Text))

Max Activating Token Index: 279

Text #14

Max Range: 5.1193. Min Range: -5.1193

Max Act: 2.1398. Min Act: -0.0001

Data Index: 521397 (C4 (Web Text))

Max Activating Token Index: 95

Text #15

Max Range: 5.1193. Min Range: -5.1193

Max Act: 2.0033. Min Act: -0.0001

Data Index: 64003 (C4 (Web Text))

Max Activating Token Index: 417

Text #16

Max Range: 5.1193. Min Range: -5.1193

Max Act: 2.0932. Min Act: -0.0001

Data Index: 575546 (C4 (Web Text))

Max Activating Token Index: 546

Text #17

Max Range: 5.1193. Min Range: -5.1193

Max Act: 1.9670. Min Act: -0.0001

Data Index: 356699 (C4 (Web Text))

Max Activating Token Index: 202

Text #18

Max Range: 5.1193. Min Range: -5.1193

Max Act: 2.1641. Min Act: -0.0001

Data Index: 634112 (C4 (Web Text))

Max Activating Token Index: 569

Text #19

Max Range: 5.1193. Min Range: -5.1193

Max Act: 2.2787. Min Act: -0.0001

Data Index: 485154 (C4 (Web Text))

Max Activating Token Index: 593