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

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

Neuron 834 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1884. Min Act: -0.0001

Data Index: 140271 (C4 (Web Text))

Max Activating Token Index: 959

Text #1

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1621. Min Act: -0.0001

Data Index: 777534 (C4 (Web Text))

Max Activating Token Index: 675

Text #2

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1462. Min Act: -0.0001

Data Index: 48015 (C4 (Web Text))

Max Activating Token Index: 773

Text #3

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1400. Min Act: -0.0001

Data Index: 82145 (C4 (Web Text))

Max Activating Token Index: 186

Text #4

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1229. Min Act: -0.0001

Data Index: 1074102 (C4 (Web Text))

Max Activating Token Index: 924

Text #5

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1435. Min Act: -0.0001

Data Index: 568089 (C4 (Web Text))

Max Activating Token Index: 526

Text #6

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1239. Min Act: -0.0001

Data Index: 916564 (C4 (Web Text))

Max Activating Token Index: 9

Text #7

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1214. Min Act: -0.0001

Data Index: 1054087 (C4 (Web Text))

Max Activating Token Index: 593

Text #8

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1173. Min Act: -0.0001

Data Index: 1107697 (C4 (Web Text))

Max Activating Token Index: 696

Text #9

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1063. Min Act: -0.0001

Data Index: 778163 (C4 (Web Text))

Max Activating Token Index: 154

Text #10

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1032. Min Act: -0.0001

Data Index: 18557 (C4 (Web Text))

Max Activating Token Index: 399

Text #11

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1071. Min Act: -0.0001

Data Index: 716110 (C4 (Web Text))

Max Activating Token Index: 473

Text #12

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.0972. Min Act: -0.0001

Data Index: 92426 (C4 (Web Text))

Max Activating Token Index: 49

Text #13

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1008. Min Act: -0.0001

Data Index: 225818 (C4 (Web Text))

Max Activating Token Index: 699

Text #14

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1046. Min Act: -0.0001

Data Index: 396303 (C4 (Web Text))

Max Activating Token Index: 147

Text #15

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1006. Min Act: -0.0001

Data Index: 909320 (C4 (Web Text))

Max Activating Token Index: 537

Text #16

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1081. Min Act: -0.0001

Data Index: 465406 (C4 (Web Text))

Max Activating Token Index: 705

Text #17

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.0978. Min Act: -0.0001

Data Index: 561070 (C4 (Web Text))

Max Activating Token Index: 296

Text #18

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.0945. Min Act: -0.0001

Data Index: 171926 (C4 (Web Text))

Max Activating Token Index: 685

Text #19

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1011. Min Act: -0.0001

Data Index: 623603 (C4 (Web Text))

Max Activating Token Index: 563