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

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

Neuron 2246 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3715. Min Range: -1.3715

Max Act: 1.3715. Min Act: -0.0001

Data Index: 634808 (C4 (Web Text))

Max Activating Token Index: 907

Text #1

Max Range: 1.3715. Min Range: -1.3715

Max Act: 1.3569. Min Act: -0.0001

Data Index: 366984 (C4 (Web Text))

Max Activating Token Index: 25

Text #2

Max Range: 1.3715. Min Range: -1.3715

Max Act: 1.3082. Min Act: -0.0001

Data Index: 915715 (C4 (Web Text))

Max Activating Token Index: 180

Text #3

Max Range: 1.3715. Min Range: -1.3715

Max Act: 1.3697. Min Act: -0.0001

Data Index: 1127189 (C4 (Web Text))

Max Activating Token Index: 185

Text #4

Max Range: 1.3715. Min Range: -1.3715

Max Act: 1.3030. Min Act: -0.0001

Data Index: 580779 (C4 (Web Text))

Max Activating Token Index: 122

Text #5

Max Range: 1.3715. Min Range: -1.3715

Max Act: 1.2553. Min Act: -0.0001

Data Index: 526015 (C4 (Web Text))

Max Activating Token Index: 477

Text #6

Max Range: 1.3715. Min Range: -1.3715

Max Act: 1.2190. Min Act: -0.0001

Data Index: 1115140 (C4 (Web Text))

Max Activating Token Index: 1010

Text #7

Max Range: 1.3715. Min Range: -1.3715

Max Act: 1.1576. Min Act: -0.0001

Data Index: 255353 (C4 (Web Text))

Max Activating Token Index: 855

Text #8

Max Range: 1.3715. Min Range: -1.3715

Max Act: 1.0036. Min Act: -0.0001

Data Index: 975353 (C4 (Web Text))

Max Activating Token Index: 912

Text #9

Max Range: 1.3715. Min Range: -1.3715

Max Act: 1.2048. Min Act: -0.0001

Data Index: 1240547 (C4 (Web Text))

Max Activating Token Index: 447

Text #10

Max Range: 1.3715. Min Range: -1.3715

Max Act: 1.1999. Min Act: -0.0001

Data Index: 834327 (C4 (Web Text))

Max Activating Token Index: 724

Text #11

Max Range: 1.3715. Min Range: -1.3715

Max Act: 1.2030. Min Act: -0.0001

Data Index: 729451 (C4 (Web Text))

Max Activating Token Index: 885

Text #12

Max Range: 1.3715. Min Range: -1.3715

Max Act: 1.1667. Min Act: -0.0001

Data Index: 134379 (C4 (Web Text))

Max Activating Token Index: 53

Text #13

Max Range: 1.3715. Min Range: -1.3715

Max Act: 1.1491. Min Act: -0.0001

Data Index: 208417 (C4 (Web Text))

Max Activating Token Index: 837

Text #14

Max Range: 1.3715. Min Range: -1.3715

Max Act: 1.1478. Min Act: -0.0001

Data Index: 775666 (C4 (Web Text))

Max Activating Token Index: 72

Text #15

Max Range: 1.3715. Min Range: -1.3715

Max Act: 1.1070. Min Act: -0.0001

Data Index: 1329554 (C4 (Web Text))

Max Activating Token Index: 843

Text #16

Max Range: 1.3715. Min Range: -1.3715

Max Act: 1.1743. Min Act: -0.0001

Data Index: 622816 (C4 (Web Text))

Max Activating Token Index: 263

Text #17

Max Range: 1.3715. Min Range: -1.3715

Max Act: 1.1056. Min Act: -0.0001

Data Index: 208406 (C4 (Web Text))

Max Activating Token Index: 203

Text #18

Max Range: 1.3715. Min Range: -1.3715

Max Act: 1.1149. Min Act: -0.0001

Data Index: 1159959 (C4 (Web Text))

Max Activating Token Index: 877

Text #19

Max Range: 1.3715. Min Range: -1.3715

Max Act: 1.1519. Min Act: -0.0001

Data Index: 194002 (C4 (Web Text))

Max Activating Token Index: 873