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

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

Neuron 3870 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3524. Min Range: -0.3524

Max Act: 0.3524. Min Act: -0.0000

Data Index: 43515 (C4 (Web Text))

Max Activating Token Index: 132

Text #1

Max Range: 0.3524. Min Range: -0.3524

Max Act: 0.2968. Min Act: -0.0000

Data Index: 750154 (C4 (Web Text))

Max Activating Token Index: 952

Text #2

Max Range: 0.3524. Min Range: -0.3524

Max Act: 0.3057. Min Act: -0.0000

Data Index: 357765 (C4 (Web Text))

Max Activating Token Index: 1012

Text #3

Max Range: 0.3524. Min Range: -0.3524

Max Act: 0.2954. Min Act: -0.0000

Data Index: 470092 (C4 (Web Text))

Max Activating Token Index: 791

Text #4

Max Range: 0.3524. Min Range: -0.3524

Max Act: 0.2854. Min Act: -0.0000

Data Index: 264000 (C4 (Web Text))

Max Activating Token Index: 878

Text #5

Max Range: 0.3524. Min Range: -0.3524

Max Act: 0.3014. Min Act: -0.0000

Data Index: 813447 (C4 (Web Text))

Max Activating Token Index: 886

Text #6

Max Range: 0.3524. Min Range: -0.3524

Max Act: 0.3012. Min Act: -0.0000

Data Index: 1245073 (C4 (Web Text))

Max Activating Token Index: 991

Text #7

Max Range: 0.3524. Min Range: -0.3524

Max Act: 0.2772. Min Act: -0.0000

Data Index: 716055 (C4 (Web Text))

Max Activating Token Index: 934

Text #8

Max Range: 0.3524. Min Range: -0.3524

Max Act: 0.2860. Min Act: -0.0000

Data Index: 327295 (C4 (Web Text))

Max Activating Token Index: 888

Text #9

Max Range: 0.3524. Min Range: -0.3524

Max Act: 0.2904. Min Act: -0.0000

Data Index: 274104 (C4 (Web Text))

Max Activating Token Index: 102

Text #10

Max Range: 0.3524. Min Range: -0.3524

Max Act: 0.2643. Min Act: -0.0000

Data Index: 118536 (C4 (Web Text))

Max Activating Token Index: 727

Text #11

Max Range: 0.3524. Min Range: -0.3524

Max Act: 0.2760. Min Act: -0.0001

Data Index: 1376054 (Python Code)

Max Activating Token Index: 103

Text #12

Max Range: 0.3524. Min Range: -0.3524

Max Act: 0.2788. Min Act: -0.0000

Data Index: 166891 (C4 (Web Text))

Max Activating Token Index: 564

Text #13

Max Range: 0.3524. Min Range: -0.3524

Max Act: 0.2350. Min Act: -0.0000

Data Index: 613378 (C4 (Web Text))

Max Activating Token Index: 700

Text #14

Max Range: 0.3524. Min Range: -0.3524

Max Act: 0.2642. Min Act: -0.0000

Data Index: 385442 (C4 (Web Text))

Max Activating Token Index: 362

Text #15

Max Range: 0.3524. Min Range: -0.3524

Max Act: 0.2553. Min Act: -0.0000

Data Index: 1030023 (C4 (Web Text))

Max Activating Token Index: 883

Text #16

Max Range: 0.3524. Min Range: -0.3524

Max Act: 0.2736. Min Act: -0.0001

Data Index: 109887 (C4 (Web Text))

Max Activating Token Index: 513

Text #17

Max Range: 0.3524. Min Range: -0.3524

Max Act: 0.2448. Min Act: -0.0000

Data Index: 1306940 (C4 (Web Text))

Max Activating Token Index: 361

Text #18

Max Range: 0.3524. Min Range: -0.3524

Max Act: 0.2774. Min Act: -0.0000

Data Index: 1062265 (C4 (Web Text))

Max Activating Token Index: 367

Text #19

Max Range: 0.3524. Min Range: -0.3524

Max Act: 0.2883. Min Act: -0.0000

Data Index: 787575 (C4 (Web Text))

Max Activating Token Index: 859