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

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

Neuron 2727 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1718. Min Range: -0.1718

Max Act: 0.1718. Min Act: -0.0001

Data Index: 693091 (C4 (Web Text))

Max Activating Token Index: 153

Text #1

Max Range: 0.1718. Min Range: -0.1718

Max Act: 0.1591. Min Act: -0.0001

Data Index: 681775 (C4 (Web Text))

Max Activating Token Index: 567

Text #2

Max Range: 0.1718. Min Range: -0.1718

Max Act: 0.1468. Min Act: -0.0001

Data Index: 566026 (C4 (Web Text))

Max Activating Token Index: 350

Text #3

Max Range: 0.1718. Min Range: -0.1718

Max Act: 0.1521. Min Act: -0.0000

Data Index: 1061631 (C4 (Web Text))

Max Activating Token Index: 777

Text #4

Max Range: 0.1718. Min Range: -0.1718

Max Act: 0.1415. Min Act: -0.0001

Data Index: 348667 (C4 (Web Text))

Max Activating Token Index: 701

Text #5

Max Range: 0.1718. Min Range: -0.1718

Max Act: 0.1296. Min Act: -0.0001

Data Index: 1308418 (C4 (Web Text))

Max Activating Token Index: 717

Text #6

Max Range: 0.1718. Min Range: -0.1718

Max Act: 0.1255. Min Act: -0.0001

Data Index: 24387 (C4 (Web Text))

Max Activating Token Index: 862

Text #7

Max Range: 0.1718. Min Range: -0.1718

Max Act: 0.1152. Min Act: -0.0001

Data Index: 772276 (C4 (Web Text))

Max Activating Token Index: 316

Text #8

Max Range: 0.1718. Min Range: -0.1718

Max Act: 0.1099. Min Act: -0.0000

Data Index: 4607 (C4 (Web Text))

Max Activating Token Index: 798

Text #9

Max Range: 0.1718. Min Range: -0.1718

Max Act: 0.1130. Min Act: -0.0000

Data Index: 519691 (C4 (Web Text))

Max Activating Token Index: 260

Text #10

Max Range: 0.1718. Min Range: -0.1718

Max Act: 0.1119. Min Act: -0.0001

Data Index: 798275 (C4 (Web Text))

Max Activating Token Index: 427

Text #11

Max Range: 0.1718. Min Range: -0.1718

Max Act: 0.1099. Min Act: -0.0001

Data Index: 993169 (C4 (Web Text))

Max Activating Token Index: 575

Text #12

Max Range: 0.1718. Min Range: -0.1718

Max Act: 0.1143. Min Act: -0.0001

Data Index: 851864 (C4 (Web Text))

Max Activating Token Index: 976

Text #13

Max Range: 0.1718. Min Range: -0.1718

Max Act: 0.1035. Min Act: -0.0001

Data Index: 839458 (C4 (Web Text))

Max Activating Token Index: 976

Text #14

Max Range: 0.1718. Min Range: -0.1718

Max Act: 0.0999. Min Act: -0.0001

Data Index: 1328472 (C4 (Web Text))

Max Activating Token Index: 818

Text #15

Max Range: 0.1718. Min Range: -0.1718

Max Act: 0.0967. Min Act: -0.0001

Data Index: 663656 (C4 (Web Text))

Max Activating Token Index: 524

Text #16

Max Range: 0.1718. Min Range: -0.1718

Max Act: 0.1044. Min Act: -0.0001

Data Index: 400632 (C4 (Web Text))

Max Activating Token Index: 575

Text #17

Max Range: 0.1718. Min Range: -0.1718

Max Act: 0.1071. Min Act: -0.0001

Data Index: 240346 (C4 (Web Text))

Max Activating Token Index: 130

Text #18

Max Range: 0.1718. Min Range: -0.1718

Max Act: 0.0981. Min Act: -0.0001

Data Index: 387581 (C4 (Web Text))

Max Activating Token Index: 75

Text #19

Max Range: 0.1718. Min Range: -0.1718

Max Act: 0.1017. Min Act: -0.0000

Data Index: 303164 (C4 (Web Text))

Max Activating Token Index: 577