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

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

Neuron 4756 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8182. Min Range: -0.8182

Max Act: 0.8051. Min Act: 0.0001

Data Index: 646920 (C4 (Web Text))

Max Activating Token Index: 18

Text #1

Max Range: 0.8182. Min Range: -0.8182

Max Act: 0.8182. Min Act: -0.0000

Data Index: 519806 (C4 (Web Text))

Max Activating Token Index: 648

Text #2

Max Range: 0.8182. Min Range: -0.8182

Max Act: 0.7239. Min Act: -0.0000

Data Index: 534579 (C4 (Web Text))

Max Activating Token Index: 294

Text #3

Max Range: 0.8182. Min Range: -0.8182

Max Act: 0.6623. Min Act: 0.0001

Data Index: 172193 (C4 (Web Text))

Max Activating Token Index: 756

Text #4

Max Range: 0.8182. Min Range: -0.8182

Max Act: 0.6895. Min Act: -0.0000

Data Index: 1218938 (C4 (Web Text))

Max Activating Token Index: 267

Text #5

Max Range: 0.8182. Min Range: -0.8182

Max Act: 0.6415. Min Act: -0.0000

Data Index: 106733 (C4 (Web Text))

Max Activating Token Index: 106

Text #6

Max Range: 0.8182. Min Range: -0.8182

Max Act: 0.6260. Min Act: -0.0000

Data Index: 915404 (C4 (Web Text))

Max Activating Token Index: 936

Text #7

Max Range: 0.8182. Min Range: -0.8182

Max Act: 0.6225. Min Act: -0.0000

Data Index: 1085445 (C4 (Web Text))

Max Activating Token Index: 69

Text #8

Max Range: 0.8182. Min Range: -0.8182

Max Act: 0.6062. Min Act: -0.0000

Data Index: 977400 (C4 (Web Text))

Max Activating Token Index: 254

Text #9

Max Range: 0.8182. Min Range: -0.8182

Max Act: 0.6195. Min Act: -0.0000

Data Index: 436998 (C4 (Web Text))

Max Activating Token Index: 702

Text #10

Max Range: 0.8182. Min Range: -0.8182

Max Act: 0.5748. Min Act: -0.0000

Data Index: 1151440 (C4 (Web Text))

Max Activating Token Index: 745

Text #11

Max Range: 0.8182. Min Range: -0.8182

Max Act: 0.5697. Min Act: -0.0000

Data Index: 946810 (C4 (Web Text))

Max Activating Token Index: 231

Text #12

Max Range: 0.8182. Min Range: -0.8182

Max Act: 0.5437. Min Act: -0.0000

Data Index: 593238 (C4 (Web Text))

Max Activating Token Index: 332

Text #13

Max Range: 0.8182. Min Range: -0.8182

Max Act: 0.5434. Min Act: -0.0000

Data Index: 890435 (C4 (Web Text))

Max Activating Token Index: 472

Text #14

Max Range: 0.8182. Min Range: -0.8182

Max Act: 0.5483. Min Act: -0.0000

Data Index: 846580 (C4 (Web Text))

Max Activating Token Index: 955

Text #15

Max Range: 0.8182. Min Range: -0.8182

Max Act: 0.5591. Min Act: 0.0000

Data Index: 499718 (C4 (Web Text))

Max Activating Token Index: 970

Text #16

Max Range: 0.8182. Min Range: -0.8182

Max Act: 0.5458. Min Act: -0.0000

Data Index: 122404 (C4 (Web Text))

Max Activating Token Index: 475

Text #17

Max Range: 0.8182. Min Range: -0.8182

Max Act: 0.5273. Min Act: 0.0000

Data Index: 325301 (C4 (Web Text))

Max Activating Token Index: 275

Text #18

Max Range: 0.8182. Min Range: -0.8182

Max Act: 0.5106. Min Act: -0.0000

Data Index: 893360 (C4 (Web Text))

Max Activating Token Index: 840

Text #19

Max Range: 0.8182. Min Range: -0.8182

Max Act: 0.5365. Min Act: -0.0000

Data Index: 34129 (C4 (Web Text))

Max Activating Token Index: 741