Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 193 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.4983. Min Range: -0.4983

Max Act: 0.4973. Min Act: -0.0000

Data Index: 1023846 (C4 (Web Text))

Max Activating Token Index: 189

Text #1

Max Range: 0.4983. Min Range: -0.4983

Max Act: 0.4983. Min Act: -0.0000

Data Index: 1172912 (C4 (Web Text))

Max Activating Token Index: 930

Text #2

Max Range: 0.4983. Min Range: -0.4983

Max Act: 0.4788. Min Act: -0.0000

Data Index: 1299240 (C4 (Web Text))

Max Activating Token Index: 570

Text #3

Max Range: 0.4983. Min Range: -0.4983

Max Act: 0.4011. Min Act: -0.0000

Data Index: 1039142 (C4 (Web Text))

Max Activating Token Index: 852

Text #4

Max Range: 0.4983. Min Range: -0.4983

Max Act: 0.4343. Min Act: -0.0000

Data Index: 1646418 (Python Code)

Max Activating Token Index: 230

Text #5

Max Range: 0.4983. Min Range: -0.4983

Max Act: 0.4341. Min Act: -0.0000

Data Index: 126953 (C4 (Web Text))

Max Activating Token Index: 901

Text #6

Max Range: 0.4983. Min Range: -0.4983

Max Act: 0.4563. Min Act: -0.0000

Data Index: 881076 (C4 (Web Text))

Max Activating Token Index: 240

Text #7

Max Range: 0.4983. Min Range: -0.4983

Max Act: 0.4534. Min Act: -0.0000

Data Index: 696233 (C4 (Web Text))

Max Activating Token Index: 28

Text #8

Max Range: 0.4983. Min Range: -0.4983

Max Act: 0.4324. Min Act: -0.0000

Data Index: 1187214 (C4 (Web Text))

Max Activating Token Index: 919

Text #9

Max Range: 0.4983. Min Range: -0.4983

Max Act: 0.4134. Min Act: -0.0000

Data Index: 375668 (C4 (Web Text))

Max Activating Token Index: 496

Text #10

Max Range: 0.4983. Min Range: -0.4983

Max Act: 0.4110. Min Act: -0.0000

Data Index: 1042143 (C4 (Web Text))

Max Activating Token Index: 858

Text #11

Max Range: 0.4983. Min Range: -0.4983

Max Act: 0.3909. Min Act: -0.0000

Data Index: 1083713 (C4 (Web Text))

Max Activating Token Index: 637

Text #12

Max Range: 0.4983. Min Range: -0.4983

Max Act: 0.3869. Min Act: -0.0000

Data Index: 1200913 (C4 (Web Text))

Max Activating Token Index: 1001

Text #13

Max Range: 0.4983. Min Range: -0.4983

Max Act: 0.4006. Min Act: -0.0000

Data Index: 536299 (C4 (Web Text))

Max Activating Token Index: 111

Text #14

Max Range: 0.4983. Min Range: -0.4983

Max Act: 0.3921. Min Act: -0.0000

Data Index: 162552 (C4 (Web Text))

Max Activating Token Index: 517

Text #15

Max Range: 0.4983. Min Range: -0.4983

Max Act: 0.4065. Min Act: -0.0000

Data Index: 1013749 (C4 (Web Text))

Max Activating Token Index: 741

Text #16

Max Range: 0.4983. Min Range: -0.4983

Max Act: 0.3770. Min Act: -0.0000

Data Index: 330999 (C4 (Web Text))

Max Activating Token Index: 751

Text #17

Max Range: 0.4983. Min Range: -0.4983

Max Act: 0.4141. Min Act: -0.0000

Data Index: 350229 (C4 (Web Text))

Max Activating Token Index: 825

Text #18

Max Range: 0.4983. Min Range: -0.4983

Max Act: 0.3761. Min Act: -0.0000

Data Index: 834102 (C4 (Web Text))

Max Activating Token Index: 457

Text #19

Max Range: 0.4983. Min Range: -0.4983

Max Act: 0.3895. Min Act: -0.0000

Data Index: 741179 (C4 (Web Text))

Max Activating Token Index: 990