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

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

Neuron 5307 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4087. Min Range: -0.4087

Max Act: 0.3907. Min Act: -0.0000

Data Index: 849636 (C4 (Web Text))

Max Activating Token Index: 349

Text #1

Max Range: 0.4087. Min Range: -0.4087

Max Act: 0.3885. Min Act: -0.0000

Data Index: 195027 (C4 (Web Text))

Max Activating Token Index: 578

Text #2

Max Range: 0.4087. Min Range: -0.4087

Max Act: 0.4087. Min Act: -0.0000

Data Index: 712225 (C4 (Web Text))

Max Activating Token Index: 931

Text #3

Max Range: 0.4087. Min Range: -0.4087

Max Act: 0.3822. Min Act: -0.0000

Data Index: 487568 (C4 (Web Text))

Max Activating Token Index: 695

Text #4

Max Range: 0.4087. Min Range: -0.4087

Max Act: 0.3802. Min Act: -0.0000

Data Index: 789949 (C4 (Web Text))

Max Activating Token Index: 989

Text #5

Max Range: 0.4087. Min Range: -0.4087

Max Act: 0.3617. Min Act: -0.0000

Data Index: 621198 (C4 (Web Text))

Max Activating Token Index: 446

Text #6

Max Range: 0.4087. Min Range: -0.4087

Max Act: 0.3611. Min Act: -0.0000

Data Index: 952711 (C4 (Web Text))

Max Activating Token Index: 675

Text #7

Max Range: 0.4087. Min Range: -0.4087

Max Act: 0.3440. Min Act: -0.0000

Data Index: 379626 (C4 (Web Text))

Max Activating Token Index: 672

Text #8

Max Range: 0.4087. Min Range: -0.4087

Max Act: 0.3640. Min Act: -0.0000

Data Index: 1221927 (C4 (Web Text))

Max Activating Token Index: 556

Text #9

Max Range: 0.4087. Min Range: -0.4087

Max Act: 0.3081. Min Act: -0.0000

Data Index: 912056 (C4 (Web Text))

Max Activating Token Index: 409

Text #10

Max Range: 0.4087. Min Range: -0.4087

Max Act: 0.3302. Min Act: -0.0000

Data Index: 413921 (C4 (Web Text))

Max Activating Token Index: 718

Text #11

Max Range: 0.4087. Min Range: -0.4087

Max Act: 0.3349. Min Act: -0.0000

Data Index: 1180436 (C4 (Web Text))

Max Activating Token Index: 235

Text #12

Max Range: 0.4087. Min Range: -0.4087

Max Act: 0.3153. Min Act: -0.0000

Data Index: 133530 (C4 (Web Text))

Max Activating Token Index: 444

Text #13

Max Range: 0.4087. Min Range: -0.4087

Max Act: 0.3117. Min Act: -0.0000

Data Index: 1031288 (C4 (Web Text))

Max Activating Token Index: 366

Text #14

Max Range: 0.4087. Min Range: -0.4087

Max Act: 0.3061. Min Act: -0.0000

Data Index: 550627 (C4 (Web Text))

Max Activating Token Index: 168

Text #15

Max Range: 0.4087. Min Range: -0.4087

Max Act: 0.3134. Min Act: -0.0000

Data Index: 699158 (C4 (Web Text))

Max Activating Token Index: 560

Text #16

Max Range: 0.4087. Min Range: -0.4087

Max Act: 0.3096. Min Act: -0.0000

Data Index: 1558049 (Python Code)

Max Activating Token Index: 144

Text #17

Max Range: 0.4087. Min Range: -0.4087

Max Act: 0.3145. Min Act: -0.0000

Data Index: 1112015 (C4 (Web Text))

Max Activating Token Index: 637

Text #18

Max Range: 0.4087. Min Range: -0.4087

Max Act: 0.2956. Min Act: 0.0000

Data Index: 1151870 (C4 (Web Text))

Max Activating Token Index: 765

Text #19

Max Range: 0.4087. Min Range: -0.4087

Max Act: 0.3040. Min Act: -0.0000

Data Index: 1111825 (C4 (Web Text))

Max Activating Token Index: 717