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

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

Neuron 384 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8418. Min Range: -0.8418

Max Act: 0.8418. Min Act: -0.0000

Data Index: 1291253 (C4 (Web Text))

Max Activating Token Index: 947

Text #1

Max Range: 0.8418. Min Range: -0.8418

Max Act: 0.7352. Min Act: -0.0000

Data Index: 51581 (C4 (Web Text))

Max Activating Token Index: 463

Text #2

Max Range: 0.8418. Min Range: -0.8418

Max Act: 0.6604. Min Act: -0.0000

Data Index: 999731 (C4 (Web Text))

Max Activating Token Index: 231

Text #3

Max Range: 0.8418. Min Range: -0.8418

Max Act: 0.6714. Min Act: -0.0000

Data Index: 1082371 (C4 (Web Text))

Max Activating Token Index: 701

Text #4

Max Range: 0.8418. Min Range: -0.8418

Max Act: 0.6243. Min Act: -0.0000

Data Index: 1119092 (C4 (Web Text))

Max Activating Token Index: 186

Text #5

Max Range: 0.8418. Min Range: -0.8418

Max Act: 0.5831. Min Act: -0.0000

Data Index: 193317 (C4 (Web Text))

Max Activating Token Index: 978

Text #6

Max Range: 0.8418. Min Range: -0.8418

Max Act: 0.5542. Min Act: -0.0000

Data Index: 308148 (C4 (Web Text))

Max Activating Token Index: 820

Text #7

Max Range: 0.8418. Min Range: -0.8418

Max Act: 0.5604. Min Act: -0.0000

Data Index: 1335708 (C4 (Web Text))

Max Activating Token Index: 263

Text #8

Max Range: 0.8418. Min Range: -0.8418

Max Act: 0.5582. Min Act: -0.0000

Data Index: 1177940 (C4 (Web Text))

Max Activating Token Index: 856

Text #9

Max Range: 0.8418. Min Range: -0.8418

Max Act: 0.5742. Min Act: -0.0000

Data Index: 653524 (C4 (Web Text))

Max Activating Token Index: 405

Text #10

Max Range: 0.8418. Min Range: -0.8418

Max Act: 0.5640. Min Act: -0.0000

Data Index: 1065970 (C4 (Web Text))

Max Activating Token Index: 269

Text #11

Max Range: 0.8418. Min Range: -0.8418

Max Act: 0.5583. Min Act: -0.0000

Data Index: 597491 (C4 (Web Text))

Max Activating Token Index: 60

Text #12

Max Range: 0.8418. Min Range: -0.8418

Max Act: 0.5221. Min Act: -0.0000

Data Index: 1059875 (C4 (Web Text))

Max Activating Token Index: 590

Text #13

Max Range: 0.8418. Min Range: -0.8418

Max Act: 0.5557. Min Act: -0.0000

Data Index: 544511 (C4 (Web Text))

Max Activating Token Index: 710

Text #14

Max Range: 0.8418. Min Range: -0.8418

Max Act: 0.5480. Min Act: -0.0000

Data Index: 681478 (C4 (Web Text))

Max Activating Token Index: 26

Text #15

Max Range: 0.8418. Min Range: -0.8418

Max Act: 0.5305. Min Act: -0.0000

Data Index: 394081 (C4 (Web Text))

Max Activating Token Index: 28

Text #16

Max Range: 0.8418. Min Range: -0.8418

Max Act: 0.5354. Min Act: -0.0000

Data Index: 157117 (C4 (Web Text))

Max Activating Token Index: 625

Text #17

Max Range: 0.8418. Min Range: -0.8418

Max Act: 0.5683. Min Act: -0.0000

Data Index: 576530 (C4 (Web Text))

Max Activating Token Index: 1020

Text #18

Max Range: 0.8418. Min Range: -0.8418

Max Act: 0.4712. Min Act: -0.0000

Data Index: 1216394 (C4 (Web Text))

Max Activating Token Index: 992

Text #19

Max Range: 0.8418. Min Range: -0.8418

Max Act: 0.5185. Min Act: -0.0000

Data Index: 1331489 (C4 (Web Text))

Max Activating Token Index: 600