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

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

Neuron 660 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7278. Min Range: -0.7278

Max Act: 0.7278. Min Act: -0.0001

Data Index: 1168384 (C4 (Web Text))

Max Activating Token Index: 386

Text #1

Max Range: 0.7278. Min Range: -0.7278

Max Act: 0.6596. Min Act: -0.0001

Data Index: 511291 (C4 (Web Text))

Max Activating Token Index: 732

Text #2

Max Range: 0.7278. Min Range: -0.7278

Max Act: 0.6197. Min Act: -0.0000

Data Index: 768384 (C4 (Web Text))

Max Activating Token Index: 736

Text #3

Max Range: 0.7278. Min Range: -0.7278

Max Act: 0.6108. Min Act: -0.0000

Data Index: 793825 (C4 (Web Text))

Max Activating Token Index: 253

Text #4

Max Range: 0.7278. Min Range: -0.7278

Max Act: 0.5902. Min Act: -0.0000

Data Index: 579245 (C4 (Web Text))

Max Activating Token Index: 304

Text #5

Max Range: 0.7278. Min Range: -0.7278

Max Act: 0.5895. Min Act: -0.0000

Data Index: 135289 (C4 (Web Text))

Max Activating Token Index: 416

Text #6

Max Range: 0.7278. Min Range: -0.7278

Max Act: 0.5818. Min Act: -0.0000

Data Index: 1359719 (C4 (Web Text))

Max Activating Token Index: 789

Text #7

Max Range: 0.7278. Min Range: -0.7278

Max Act: 0.5513. Min Act: -0.0000

Data Index: 784434 (C4 (Web Text))

Max Activating Token Index: 560

Text #8

Max Range: 0.7278. Min Range: -0.7278

Max Act: 0.5390. Min Act: -0.0000

Data Index: 1231034 (C4 (Web Text))

Max Activating Token Index: 471

Text #9

Max Range: 0.7278. Min Range: -0.7278

Max Act: 0.5528. Min Act: -0.0000

Data Index: 621890 (C4 (Web Text))

Max Activating Token Index: 683

Text #10

Max Range: 0.7278. Min Range: -0.7278

Max Act: 0.5449. Min Act: -0.0000

Data Index: 129351 (C4 (Web Text))

Max Activating Token Index: 92

Text #11

Max Range: 0.7278. Min Range: -0.7278

Max Act: 0.5219. Min Act: -0.0000

Data Index: 816303 (C4 (Web Text))

Max Activating Token Index: 263

Text #12

Max Range: 0.7278. Min Range: -0.7278

Max Act: 0.5141. Min Act: -0.0000

Data Index: 1248089 (C4 (Web Text))

Max Activating Token Index: 274

Text #13

Max Range: 0.7278. Min Range: -0.7278

Max Act: 0.5124. Min Act: -0.0000

Data Index: 881516 (C4 (Web Text))

Max Activating Token Index: 7

Text #14

Max Range: 0.7278. Min Range: -0.7278

Max Act: 0.5081. Min Act: -0.0000

Data Index: 299024 (C4 (Web Text))

Max Activating Token Index: 933

Text #15

Max Range: 0.7278. Min Range: -0.7278

Max Act: 0.5086. Min Act: -0.0001

Data Index: 55084 (C4 (Web Text))

Max Activating Token Index: 720

Text #16

Max Range: 0.7278. Min Range: -0.7278

Max Act: 0.5091. Min Act: -0.0001

Data Index: 446683 (C4 (Web Text))

Max Activating Token Index: 377

Text #17

Max Range: 0.7278. Min Range: -0.7278

Max Act: 0.5078. Min Act: -0.0000

Data Index: 451110 (C4 (Web Text))

Max Activating Token Index: 282

Text #18

Max Range: 0.7278. Min Range: -0.7278

Max Act: 0.4864. Min Act: -0.0000

Data Index: 910645 (C4 (Web Text))

Max Activating Token Index: 701

Text #19

Max Range: 0.7278. Min Range: -0.7278

Max Act: 0.5039. Min Act: -0.0000

Data Index: 731662 (C4 (Web Text))

Max Activating Token Index: 448