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

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

Neuron 3831 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3477. Min Range: -1.3477

Max Act: 1.3477. Min Act: -0.0001

Data Index: 917894 (C4 (Web Text))

Max Activating Token Index: 773

Text #1

Max Range: 1.3477. Min Range: -1.3477

Max Act: 1.3242. Min Act: -0.0001

Data Index: 633312 (C4 (Web Text))

Max Activating Token Index: 978

Text #2

Max Range: 1.3477. Min Range: -1.3477

Max Act: 1.1406. Min Act: -0.0001

Data Index: 219544 (C4 (Web Text))

Max Activating Token Index: 257

Text #3

Max Range: 1.3477. Min Range: -1.3477

Max Act: 1.2012. Min Act: -0.0001

Data Index: 620272 (C4 (Web Text))

Max Activating Token Index: 402

Text #4

Max Range: 1.3477. Min Range: -1.3477

Max Act: 1.1361. Min Act: -0.0001

Data Index: 284730 (C4 (Web Text))

Max Activating Token Index: 797

Text #5

Max Range: 1.3477. Min Range: -1.3477

Max Act: 1.1187. Min Act: -0.0001

Data Index: 332162 (C4 (Web Text))

Max Activating Token Index: 591

Text #6

Max Range: 1.3477. Min Range: -1.3477

Max Act: 1.1053. Min Act: -0.0001

Data Index: 638747 (C4 (Web Text))

Max Activating Token Index: 37

Text #7

Max Range: 1.3477. Min Range: -1.3477

Max Act: 1.1305. Min Act: -0.0001

Data Index: 86829 (C4 (Web Text))

Max Activating Token Index: 876

Text #8

Max Range: 1.3477. Min Range: -1.3477

Max Act: 1.1706. Min Act: -0.0001

Data Index: 504773 (C4 (Web Text))

Max Activating Token Index: 770

Text #9

Max Range: 1.3477. Min Range: -1.3477

Max Act: 1.1178. Min Act: -0.0001

Data Index: 1206008 (C4 (Web Text))

Max Activating Token Index: 782

Text #10

Max Range: 1.3477. Min Range: -1.3477

Max Act: 1.1084. Min Act: -0.0001

Data Index: 93141 (C4 (Web Text))

Max Activating Token Index: 398

Text #11

Max Range: 1.3477. Min Range: -1.3477

Max Act: 1.1643. Min Act: -0.0001

Data Index: 996807 (C4 (Web Text))

Max Activating Token Index: 985

Text #12

Max Range: 1.3477. Min Range: -1.3477

Max Act: 1.0657. Min Act: -0.0001

Data Index: 258761 (C4 (Web Text))

Max Activating Token Index: 273

Text #13

Max Range: 1.3477. Min Range: -1.3477

Max Act: 1.0569. Min Act: -0.0001

Data Index: 629697 (C4 (Web Text))

Max Activating Token Index: 921

Text #14

Max Range: 1.3477. Min Range: -1.3477

Max Act: 1.1200. Min Act: -0.0001

Data Index: 877958 (C4 (Web Text))

Max Activating Token Index: 442

Text #15

Max Range: 1.3477. Min Range: -1.3477

Max Act: 1.0689. Min Act: -0.0001

Data Index: 73757 (C4 (Web Text))

Max Activating Token Index: 489

Text #16

Max Range: 1.3477. Min Range: -1.3477

Max Act: 1.0550. Min Act: -0.0001

Data Index: 287654 (C4 (Web Text))

Max Activating Token Index: 196

Text #17

Max Range: 1.3477. Min Range: -1.3477

Max Act: 1.0533. Min Act: -0.0001

Data Index: 825650 (C4 (Web Text))

Max Activating Token Index: 629

Text #18

Max Range: 1.3477. Min Range: -1.3477

Max Act: 1.0667. Min Act: -0.0001

Data Index: 1100414 (C4 (Web Text))

Max Activating Token Index: 909

Text #19

Max Range: 1.3477. Min Range: -1.3477

Max Act: 1.0060. Min Act: -0.0001

Data Index: 628824 (C4 (Web Text))

Max Activating Token Index: 205