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

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

Neuron 5111 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9265. Min Range: -1.9265

Max Act: 1.9265. Min Act: -0.0000

Data Index: 35828 (C4 (Web Text))

Max Activating Token Index: 585

Text #1

Max Range: 1.9265. Min Range: -1.9265

Max Act: 1.6882. Min Act: -0.0000

Data Index: 470565 (C4 (Web Text))

Max Activating Token Index: 181

Text #2

Max Range: 1.9265. Min Range: -1.9265

Max Act: 1.6204. Min Act: -0.0000

Data Index: 603101 (C4 (Web Text))

Max Activating Token Index: 902

Text #3

Max Range: 1.9265. Min Range: -1.9265

Max Act: 1.3173. Min Act: -0.0000

Data Index: 1202655 (C4 (Web Text))

Max Activating Token Index: 814

Text #4

Max Range: 1.9265. Min Range: -1.9265

Max Act: 0.7569. Min Act: -0.0000

Data Index: 904990 (C4 (Web Text))

Max Activating Token Index: 496

Text #5

Max Range: 1.9265. Min Range: -1.9265

Max Act: 0.6661. Min Act: -0.0000

Data Index: 910779 (C4 (Web Text))

Max Activating Token Index: 839

Text #6

Max Range: 1.9265. Min Range: -1.9265

Max Act: 0.6626. Min Act: -0.0000

Data Index: 574300 (C4 (Web Text))

Max Activating Token Index: 719

Text #7

Max Range: 1.9265. Min Range: -1.9265

Max Act: 0.6571. Min Act: 0.0000

Data Index: 1352299 (C4 (Web Text))

Max Activating Token Index: 506

Text #8

Max Range: 1.9265. Min Range: -1.9265

Max Act: 0.6227. Min Act: -0.0000

Data Index: 862553 (C4 (Web Text))

Max Activating Token Index: 456

Text #9

Max Range: 1.9265. Min Range: -1.9265

Max Act: 0.6020. Min Act: -0.0000

Data Index: 974875 (C4 (Web Text))

Max Activating Token Index: 898

Text #10

Max Range: 1.9265. Min Range: -1.9265

Max Act: 0.5403. Min Act: 0.0004

Data Index: 904185 (C4 (Web Text))

Max Activating Token Index: 928

Text #11

Max Range: 1.9265. Min Range: -1.9265

Max Act: 0.5152. Min Act: -0.0000

Data Index: 640218 (C4 (Web Text))

Max Activating Token Index: 538

Text #12

Max Range: 1.9265. Min Range: -1.9265

Max Act: 0.4976. Min Act: -0.0000

Data Index: 1279524 (C4 (Web Text))

Max Activating Token Index: 738

Text #13

Max Range: 1.9265. Min Range: -1.9265

Max Act: 0.4930. Min Act: -0.0000

Data Index: 1046106 (C4 (Web Text))

Max Activating Token Index: 552

Text #14

Max Range: 1.9265. Min Range: -1.9265

Max Act: 0.4678. Min Act: -0.0000

Data Index: 1336173 (C4 (Web Text))

Max Activating Token Index: 1002

Text #15

Max Range: 1.9265. Min Range: -1.9265

Max Act: 0.4808. Min Act: -0.0000

Data Index: 818940 (C4 (Web Text))

Max Activating Token Index: 966

Text #16

Max Range: 1.9265. Min Range: -1.9265

Max Act: 0.4464. Min Act: 0.0001

Data Index: 494634 (C4 (Web Text))

Max Activating Token Index: 449

Text #17

Max Range: 1.9265. Min Range: -1.9265

Max Act: 0.4453. Min Act: -0.0000

Data Index: 72819 (C4 (Web Text))

Max Activating Token Index: 686

Text #18

Max Range: 1.9265. Min Range: -1.9265

Max Act: 0.4460. Min Act: -0.0000

Data Index: 922216 (C4 (Web Text))

Max Activating Token Index: 128

Text #19

Max Range: 1.9265. Min Range: -1.9265

Max Act: 0.4231. Min Act: -0.0000

Data Index: 730889 (C4 (Web Text))

Max Activating Token Index: 95