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

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

Neuron 3302 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: 0.4174. Min Range: -0.4174

Max Act: 0.4174. Min Act: -0.0001

Data Index: 668511 (C4 (Web Text))

Max Activating Token Index: 325

Text #1

Max Range: 0.4174. Min Range: -0.4174

Max Act: 0.3722. Min Act: -0.0001

Data Index: 351006 (C4 (Web Text))

Max Activating Token Index: 851

Text #2

Max Range: 0.4174. Min Range: -0.4174

Max Act: 0.3816. Min Act: -0.0000

Data Index: 616456 (C4 (Web Text))

Max Activating Token Index: 991

Text #3

Max Range: 0.4174. Min Range: -0.4174

Max Act: 0.3840. Min Act: -0.0001

Data Index: 660337 (C4 (Web Text))

Max Activating Token Index: 626

Text #4

Max Range: 0.4174. Min Range: -0.4174

Max Act: 0.3656. Min Act: -0.0001

Data Index: 488882 (C4 (Web Text))

Max Activating Token Index: 90

Text #5

Max Range: 0.4174. Min Range: -0.4174

Max Act: 0.3828. Min Act: -0.0000

Data Index: 653960 (C4 (Web Text))

Max Activating Token Index: 164

Text #6

Max Range: 0.4174. Min Range: -0.4174

Max Act: 0.3845. Min Act: -0.0001

Data Index: 303073 (C4 (Web Text))

Max Activating Token Index: 325

Text #7

Max Range: 0.4174. Min Range: -0.4174

Max Act: 0.3582. Min Act: -0.0000

Data Index: 574970 (C4 (Web Text))

Max Activating Token Index: 456

Text #8

Max Range: 0.4174. Min Range: -0.4174

Max Act: 0.3170. Min Act: -0.0000

Data Index: 1183003 (C4 (Web Text))

Max Activating Token Index: 167

Text #9

Max Range: 0.4174. Min Range: -0.4174

Max Act: 0.3176. Min Act: -0.0000

Data Index: 1356409 (C4 (Web Text))

Max Activating Token Index: 993

Text #10

Max Range: 0.4174. Min Range: -0.4174

Max Act: 0.3197. Min Act: -0.0001

Data Index: 331952 (C4 (Web Text))

Max Activating Token Index: 120

Text #11

Max Range: 0.4174. Min Range: -0.4174

Max Act: 0.3189. Min Act: -0.0000

Data Index: 752671 (C4 (Web Text))

Max Activating Token Index: 912

Text #12

Max Range: 0.4174. Min Range: -0.4174

Max Act: 0.3080. Min Act: -0.0000

Data Index: 1271321 (C4 (Web Text))

Max Activating Token Index: 364

Text #13

Max Range: 0.4174. Min Range: -0.4174

Max Act: 0.3063. Min Act: -0.0000

Data Index: 27356 (C4 (Web Text))

Max Activating Token Index: 862

Text #14

Max Range: 0.4174. Min Range: -0.4174

Max Act: 0.3192. Min Act: -0.0001

Data Index: 620415 (C4 (Web Text))

Max Activating Token Index: 806

Text #15

Max Range: 0.4174. Min Range: -0.4174

Max Act: 0.3143. Min Act: -0.0001

Data Index: 673424 (C4 (Web Text))

Max Activating Token Index: 763

Text #16

Max Range: 0.4174. Min Range: -0.4174

Max Act: 0.3020. Min Act: -0.0000

Data Index: 194168 (C4 (Web Text))

Max Activating Token Index: 584

Text #17

Max Range: 0.4174. Min Range: -0.4174

Max Act: 0.3106. Min Act: -0.0000

Data Index: 1012738 (C4 (Web Text))

Max Activating Token Index: 852

Text #18

Max Range: 0.4174. Min Range: -0.4174

Max Act: 0.3005. Min Act: -0.0001

Data Index: 20365 (C4 (Web Text))

Max Activating Token Index: 412

Text #19

Max Range: 0.4174. Min Range: -0.4174

Max Act: 0.3114. Min Act: -0.0000

Data Index: 779710 (C4 (Web Text))

Max Activating Token Index: 676