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

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

Neuron 3577 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: 1.3448. Min Range: -1.3448

Max Act: 1.3448. Min Act: -0.0000

Data Index: 118753 (C4 (Web Text))

Max Activating Token Index: 486

Text #1

Max Range: 1.3448. Min Range: -1.3448

Max Act: 1.2099. Min Act: -0.0000

Data Index: 40390 (C4 (Web Text))

Max Activating Token Index: 517

Text #2

Max Range: 1.3448. Min Range: -1.3448

Max Act: 1.2391. Min Act: -0.0001

Data Index: 523010 (C4 (Web Text))

Max Activating Token Index: 120

Text #3

Max Range: 1.3448. Min Range: -1.3448

Max Act: 0.9803. Min Act: -0.0000

Data Index: 1297371 (C4 (Web Text))

Max Activating Token Index: 567

Text #4

Max Range: 1.3448. Min Range: -1.3448

Max Act: 1.0549. Min Act: -0.0001

Data Index: 1444651 (Python Code)

Max Activating Token Index: 862

Text #5

Max Range: 1.3448. Min Range: -1.3448

Max Act: 0.8850. Min Act: -0.0000

Data Index: 1074942 (C4 (Web Text))

Max Activating Token Index: 203

Text #6

Max Range: 1.3448. Min Range: -1.3448

Max Act: 0.9621. Min Act: -0.0001

Data Index: 1648536 (Python Code)

Max Activating Token Index: 336

Text #7

Max Range: 1.3448. Min Range: -1.3448

Max Act: 0.9184. Min Act: -0.0001

Data Index: 1375953 (Python Code)

Max Activating Token Index: 598

Text #8

Max Range: 1.3448. Min Range: -1.3448

Max Act: 0.8573. Min Act: -0.0000

Data Index: 679788 (C4 (Web Text))

Max Activating Token Index: 587

Text #9

Max Range: 1.3448. Min Range: -1.3448

Max Act: 0.9076. Min Act: -0.0000

Data Index: 50502 (C4 (Web Text))

Max Activating Token Index: 58

Text #10

Max Range: 1.3448. Min Range: -1.3448

Max Act: 0.9065. Min Act: -0.0000

Data Index: 170458 (C4 (Web Text))

Max Activating Token Index: 793

Text #11

Max Range: 1.3448. Min Range: -1.3448

Max Act: 0.8260. Min Act: -0.0000

Data Index: 21673 (C4 (Web Text))

Max Activating Token Index: 946

Text #12

Max Range: 1.3448. Min Range: -1.3448

Max Act: 0.8141. Min Act: -0.0000

Data Index: 1184878 (C4 (Web Text))

Max Activating Token Index: 576

Text #13

Max Range: 1.3448. Min Range: -1.3448

Max Act: 0.7974. Min Act: -0.0001

Data Index: 1379344 (Python Code)

Max Activating Token Index: 828

Text #14

Max Range: 1.3448. Min Range: -1.3448

Max Act: 0.7833. Min Act: -0.0000

Data Index: 1062179 (C4 (Web Text))

Max Activating Token Index: 871

Text #15

Max Range: 1.3448. Min Range: -1.3448

Max Act: 0.9419. Min Act: -0.0000

Data Index: 1011725 (C4 (Web Text))

Max Activating Token Index: 901

Text #16

Max Range: 1.3448. Min Range: -1.3448

Max Act: 0.8006. Min Act: -0.0001

Data Index: 1409652 (Python Code)

Max Activating Token Index: 477

Text #17

Max Range: 1.3448. Min Range: -1.3448

Max Act: 0.7616. Min Act: -0.0001

Data Index: 1565841 (Python Code)

Max Activating Token Index: 235

Text #18

Max Range: 1.3448. Min Range: -1.3448

Max Act: 0.7758. Min Act: -0.0000

Data Index: 115788 (C4 (Web Text))

Max Activating Token Index: 182

Text #19

Max Range: 1.3448. Min Range: -1.3448

Max Act: 0.7790. Min Act: -0.0001

Data Index: 1391561 (Python Code)

Max Activating Token Index: 105