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

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

Neuron 4871 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7464. Min Range: -0.7464

Max Act: 0.7464. Min Act: -0.0000

Data Index: 961342 (C4 (Web Text))

Max Activating Token Index: 488

Text #1

Max Range: 0.7464. Min Range: -0.7464

Max Act: 0.7082. Min Act: -0.0000

Data Index: 1329605 (C4 (Web Text))

Max Activating Token Index: 435

Text #2

Max Range: 0.7464. Min Range: -0.7464

Max Act: 0.7073. Min Act: -0.0000

Data Index: 790966 (C4 (Web Text))

Max Activating Token Index: 598

Text #3

Max Range: 0.7464. Min Range: -0.7464

Max Act: 0.6134. Min Act: -0.0000

Data Index: 438801 (C4 (Web Text))

Max Activating Token Index: 953

Text #4

Max Range: 0.7464. Min Range: -0.7464

Max Act: 0.6021. Min Act: -0.0000

Data Index: 678519 (C4 (Web Text))

Max Activating Token Index: 247

Text #5

Max Range: 0.7464. Min Range: -0.7464

Max Act: 0.5846. Min Act: 0.0000

Data Index: 808307 (C4 (Web Text))

Max Activating Token Index: 887

Text #6

Max Range: 0.7464. Min Range: -0.7464

Max Act: 0.5885. Min Act: -0.0000

Data Index: 1087722 (C4 (Web Text))

Max Activating Token Index: 789

Text #7

Max Range: 0.7464. Min Range: -0.7464

Max Act: 0.5250. Min Act: -0.0000

Data Index: 712193 (C4 (Web Text))

Max Activating Token Index: 439

Text #8

Max Range: 0.7464. Min Range: -0.7464

Max Act: 0.5355. Min Act: 0.0000

Data Index: 819114 (C4 (Web Text))

Max Activating Token Index: 680

Text #9

Max Range: 0.7464. Min Range: -0.7464

Max Act: 0.4928. Min Act: 0.0000

Data Index: 97786 (C4 (Web Text))

Max Activating Token Index: 218

Text #10

Max Range: 0.7464. Min Range: -0.7464

Max Act: 0.4802. Min Act: -0.0000

Data Index: 955972 (C4 (Web Text))

Max Activating Token Index: 976

Text #11

Max Range: 0.7464. Min Range: -0.7464

Max Act: 0.5085. Min Act: 0.0000

Data Index: 484161 (C4 (Web Text))

Max Activating Token Index: 118

Text #12

Max Range: 0.7464. Min Range: -0.7464

Max Act: 0.4787. Min Act: -0.0000

Data Index: 992170 (C4 (Web Text))

Max Activating Token Index: 688

Text #13

Max Range: 0.7464. Min Range: -0.7464

Max Act: 0.4895. Min Act: -0.0000

Data Index: 913070 (C4 (Web Text))

Max Activating Token Index: 26

Text #14

Max Range: 0.7464. Min Range: -0.7464

Max Act: 0.4886. Min Act: -0.0000

Data Index: 592366 (C4 (Web Text))

Max Activating Token Index: 466

Text #15

Max Range: 0.7464. Min Range: -0.7464

Max Act: 0.4872. Min Act: -0.0000

Data Index: 307812 (C4 (Web Text))

Max Activating Token Index: 564

Text #16

Max Range: 0.7464. Min Range: -0.7464

Max Act: 0.4861. Min Act: -0.0000

Data Index: 78469 (C4 (Web Text))

Max Activating Token Index: 379

Text #17

Max Range: 0.7464. Min Range: -0.7464

Max Act: 0.4815. Min Act: -0.0000

Data Index: 806440 (C4 (Web Text))

Max Activating Token Index: 501

Text #18

Max Range: 0.7464. Min Range: -0.7464

Max Act: 0.4946. Min Act: -0.0000

Data Index: 695209 (C4 (Web Text))

Max Activating Token Index: 436

Text #19

Max Range: 0.7464. Min Range: -0.7464

Max Act: 0.4947. Min Act: -0.0000

Data Index: 1270473 (C4 (Web Text))

Max Activating Token Index: 443