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

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

Neuron 265 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6551. Min Range: -0.6551

Max Act: 0.6551. Min Act: -0.0000

Data Index: 918212 (C4 (Web Text))

Max Activating Token Index: 155

Text #1

Max Range: 0.6551. Min Range: -0.6551

Max Act: 0.6403. Min Act: -0.0000

Data Index: 1336693 (C4 (Web Text))

Max Activating Token Index: 203

Text #2

Max Range: 0.6551. Min Range: -0.6551

Max Act: 0.5823. Min Act: -0.0000

Data Index: 1297595 (C4 (Web Text))

Max Activating Token Index: 97

Text #3

Max Range: 0.6551. Min Range: -0.6551

Max Act: 0.6009. Min Act: -0.0000

Data Index: 1167923 (C4 (Web Text))

Max Activating Token Index: 114

Text #4

Max Range: 0.6551. Min Range: -0.6551

Max Act: 0.5818. Min Act: -0.0000

Data Index: 1195392 (C4 (Web Text))

Max Activating Token Index: 693

Text #5

Max Range: 0.6551. Min Range: -0.6551

Max Act: 0.5425. Min Act: -0.0000

Data Index: 884053 (C4 (Web Text))

Max Activating Token Index: 797

Text #6

Max Range: 0.6551. Min Range: -0.6551

Max Act: 0.5529. Min Act: -0.0000

Data Index: 1226925 (C4 (Web Text))

Max Activating Token Index: 681

Text #7

Max Range: 0.6551. Min Range: -0.6551

Max Act: 0.5309. Min Act: -0.0000

Data Index: 1130349 (C4 (Web Text))

Max Activating Token Index: 188

Text #8

Max Range: 0.6551. Min Range: -0.6551

Max Act: 0.6062. Min Act: -0.0000

Data Index: 253902 (C4 (Web Text))

Max Activating Token Index: 230

Text #9

Max Range: 0.6551. Min Range: -0.6551

Max Act: 0.5503. Min Act: -0.0000

Data Index: 1313249 (C4 (Web Text))

Max Activating Token Index: 262

Text #10

Max Range: 0.6551. Min Range: -0.6551

Max Act: 0.5636. Min Act: -0.0000

Data Index: 1253588 (C4 (Web Text))

Max Activating Token Index: 551

Text #11

Max Range: 0.6551. Min Range: -0.6551

Max Act: 0.5218. Min Act: -0.0000

Data Index: 988687 (C4 (Web Text))

Max Activating Token Index: 151

Text #12

Max Range: 0.6551. Min Range: -0.6551

Max Act: 0.5295. Min Act: -0.0000

Data Index: 275458 (C4 (Web Text))

Max Activating Token Index: 425

Text #13

Max Range: 0.6551. Min Range: -0.6551

Max Act: 0.5338. Min Act: -0.0000

Data Index: 1347370 (C4 (Web Text))

Max Activating Token Index: 249

Text #14

Max Range: 0.6551. Min Range: -0.6551

Max Act: 0.4903. Min Act: -0.0000

Data Index: 1265651 (C4 (Web Text))

Max Activating Token Index: 667

Text #15

Max Range: 0.6551. Min Range: -0.6551

Max Act: 0.4654. Min Act: -0.0000

Data Index: 496126 (C4 (Web Text))

Max Activating Token Index: 841

Text #16

Max Range: 0.6551. Min Range: -0.6551

Max Act: 0.4890. Min Act: -0.0000

Data Index: 931134 (C4 (Web Text))

Max Activating Token Index: 44

Text #17

Max Range: 0.6551. Min Range: -0.6551

Max Act: 0.4579. Min Act: -0.0000

Data Index: 933718 (C4 (Web Text))

Max Activating Token Index: 850

Text #18

Max Range: 0.6551. Min Range: -0.6551

Max Act: 0.4988. Min Act: -0.0000

Data Index: 784276 (C4 (Web Text))

Max Activating Token Index: 871

Text #19

Max Range: 0.6551. Min Range: -0.6551

Max Act: 0.4751. Min Act: -0.0000

Data Index: 717768 (C4 (Web Text))

Max Activating Token Index: 265