Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2521 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.8020. Min Range: -1.8020

Max Act: 1.8020. Min Act: -0.0001

Data Index: 1097092 (C4 (Web Text))

Max Activating Token Index: 240

Text #1

Max Range: 1.8020. Min Range: -1.8020

Max Act: 1.7462. Min Act: -0.0001

Data Index: 656005 (C4 (Web Text))

Max Activating Token Index: 14

Text #2

Max Range: 1.8020. Min Range: -1.8020

Max Act: 1.5304. Min Act: -0.0001

Data Index: 711476 (C4 (Web Text))

Max Activating Token Index: 12

Text #3

Max Range: 1.8020. Min Range: -1.8020

Max Act: 1.4439. Min Act: -0.0001

Data Index: 744408 (C4 (Web Text))

Max Activating Token Index: 238

Text #4

Max Range: 1.8020. Min Range: -1.8020

Max Act: 1.3929. Min Act: -0.0001

Data Index: 578527 (C4 (Web Text))

Max Activating Token Index: 936

Text #5

Max Range: 1.8020. Min Range: -1.8020

Max Act: 1.2028. Min Act: -0.0001

Data Index: 32471 (C4 (Web Text))

Max Activating Token Index: 167

Text #6

Max Range: 1.8020. Min Range: -1.8020

Max Act: 1.3079. Min Act: -0.0001

Data Index: 1155269 (C4 (Web Text))

Max Activating Token Index: 24

Text #7

Max Range: 1.8020. Min Range: -1.8020

Max Act: 1.2376. Min Act: -0.0001

Data Index: 1296660 (C4 (Web Text))

Max Activating Token Index: 244

Text #8

Max Range: 1.8020. Min Range: -1.8020

Max Act: 1.1649. Min Act: -0.0001

Data Index: 1387398 (Python Code)

Max Activating Token Index: 744

Text #9

Max Range: 1.8020. Min Range: -1.8020

Max Act: 1.2630. Min Act: -0.0001

Data Index: 1429991 (Python Code)

Max Activating Token Index: 273

Text #10

Max Range: 1.8020. Min Range: -1.8020

Max Act: 1.1135. Min Act: -0.0001

Data Index: 54777 (C4 (Web Text))

Max Activating Token Index: 240

Text #11

Max Range: 1.8020. Min Range: -1.8020

Max Act: 1.1515. Min Act: -0.0001

Data Index: 1036699 (C4 (Web Text))

Max Activating Token Index: 690

Text #12

Max Range: 1.8020. Min Range: -1.8020

Max Act: 1.3152. Min Act: -0.0001

Data Index: 375442 (C4 (Web Text))

Max Activating Token Index: 767

Text #13

Max Range: 1.8020. Min Range: -1.8020

Max Act: 1.1631. Min Act: -0.0001

Data Index: 947424 (C4 (Web Text))

Max Activating Token Index: 139

Text #14

Max Range: 1.8020. Min Range: -1.8020

Max Act: 1.1638. Min Act: -0.0001

Data Index: 51778 (C4 (Web Text))

Max Activating Token Index: 855

Text #15

Max Range: 1.8020. Min Range: -1.8020

Max Act: 1.1899. Min Act: -0.0001

Data Index: 897699 (C4 (Web Text))

Max Activating Token Index: 313

Text #16

Max Range: 1.8020. Min Range: -1.8020

Max Act: 1.1825. Min Act: -0.0001

Data Index: 769499 (C4 (Web Text))

Max Activating Token Index: 190

Text #17

Max Range: 1.8020. Min Range: -1.8020

Max Act: 1.1188. Min Act: -0.0001

Data Index: 316868 (C4 (Web Text))

Max Activating Token Index: 883

Text #18

Max Range: 1.8020. Min Range: -1.8020

Max Act: 1.1433. Min Act: -0.0001

Data Index: 847573 (C4 (Web Text))

Max Activating Token Index: 834

Text #19

Max Range: 1.8020. Min Range: -1.8020

Max Act: 1.0456. Min Act: -0.0001

Data Index: 685173 (C4 (Web Text))

Max Activating Token Index: 380