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

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

Neuron 2001 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: 0.1827. Min Range: -0.1827

Max Act: 0.1827. Min Act: -0.0000

Data Index: 757888 (C4 (Web Text))

Max Activating Token Index: 264

Text #1

Max Range: 0.1827. Min Range: -0.1827

Max Act: 0.1692. Min Act: -0.0000

Data Index: 1003146 (C4 (Web Text))

Max Activating Token Index: 526

Text #2

Max Range: 0.1827. Min Range: -0.1827

Max Act: 0.1538. Min Act: -0.0000

Data Index: 357510 (C4 (Web Text))

Max Activating Token Index: 605

Text #3

Max Range: 0.1827. Min Range: -0.1827

Max Act: 0.1540. Min Act: -0.0001

Data Index: 457952 (C4 (Web Text))

Max Activating Token Index: 611

Text #4

Max Range: 0.1827. Min Range: -0.1827

Max Act: 0.1544. Min Act: -0.0000

Data Index: 1202320 (C4 (Web Text))

Max Activating Token Index: 955

Text #5

Max Range: 0.1827. Min Range: -0.1827

Max Act: 0.1300. Min Act: -0.0000

Data Index: 1292062 (C4 (Web Text))

Max Activating Token Index: 163

Text #6

Max Range: 0.1827. Min Range: -0.1827

Max Act: 0.1221. Min Act: -0.0000

Data Index: 357498 (C4 (Web Text))

Max Activating Token Index: 438

Text #7

Max Range: 0.1827. Min Range: -0.1827

Max Act: 0.1128. Min Act: -0.0000

Data Index: 1328931 (C4 (Web Text))

Max Activating Token Index: 646

Text #8

Max Range: 0.1827. Min Range: -0.1827

Max Act: 0.1222. Min Act: -0.0000

Data Index: 248169 (C4 (Web Text))

Max Activating Token Index: 318

Text #9

Max Range: 0.1827. Min Range: -0.1827

Max Act: 0.1183. Min Act: -0.0001

Data Index: 1006891 (C4 (Web Text))

Max Activating Token Index: 653

Text #10

Max Range: 0.1827. Min Range: -0.1827

Max Act: 0.1173. Min Act: -0.0000

Data Index: 250515 (C4 (Web Text))

Max Activating Token Index: 205

Text #11

Max Range: 0.1827. Min Range: -0.1827

Max Act: 0.1127. Min Act: -0.0000

Data Index: 38438 (C4 (Web Text))

Max Activating Token Index: 584

Text #12

Max Range: 0.1827. Min Range: -0.1827

Max Act: 0.1080. Min Act: -0.0000

Data Index: 1150315 (C4 (Web Text))

Max Activating Token Index: 616

Text #13

Max Range: 0.1827. Min Range: -0.1827

Max Act: 0.1107. Min Act: -0.0000

Data Index: 741784 (C4 (Web Text))

Max Activating Token Index: 147

Text #14

Max Range: 0.1827. Min Range: -0.1827

Max Act: 0.1093. Min Act: -0.0001

Data Index: 375590 (C4 (Web Text))

Max Activating Token Index: 627

Text #15

Max Range: 0.1827. Min Range: -0.1827

Max Act: 0.1128. Min Act: -0.0000

Data Index: 816270 (C4 (Web Text))

Max Activating Token Index: 138

Text #16

Max Range: 0.1827. Min Range: -0.1827

Max Act: 0.1017. Min Act: -0.0001

Data Index: 148992 (C4 (Web Text))

Max Activating Token Index: 314

Text #17

Max Range: 0.1827. Min Range: -0.1827

Max Act: 0.1119. Min Act: -0.0000

Data Index: 567114 (C4 (Web Text))

Max Activating Token Index: 172

Text #18

Max Range: 0.1827. Min Range: -0.1827

Max Act: 0.1135. Min Act: -0.0000

Data Index: 831741 (C4 (Web Text))

Max Activating Token Index: 443

Text #19

Max Range: 0.1827. Min Range: -0.1827

Max Act: 0.1005. Min Act: -0.0000

Data Index: 917100 (C4 (Web Text))

Max Activating Token Index: 204