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

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

Neuron 3237 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: 0.3536. Min Range: -0.3536

Max Act: 0.3536. Min Act: -0.0000

Data Index: 1123967 (C4 (Web Text))

Max Activating Token Index: 199

Text #1

Max Range: 0.3536. Min Range: -0.3536

Max Act: 0.3019. Min Act: -0.0000

Data Index: 1348980 (C4 (Web Text))

Max Activating Token Index: 221

Text #2

Max Range: 0.3536. Min Range: -0.3536

Max Act: 0.3015. Min Act: -0.0000

Data Index: 1092752 (C4 (Web Text))

Max Activating Token Index: 255

Text #3

Max Range: 0.3536. Min Range: -0.3536

Max Act: 0.3107. Min Act: -0.0000

Data Index: 701419 (C4 (Web Text))

Max Activating Token Index: 458

Text #4

Max Range: 0.3536. Min Range: -0.3536

Max Act: 0.3131. Min Act: -0.0000

Data Index: 199285 (C4 (Web Text))

Max Activating Token Index: 901

Text #5

Max Range: 0.3536. Min Range: -0.3536

Max Act: 0.3021. Min Act: -0.0000

Data Index: 261823 (C4 (Web Text))

Max Activating Token Index: 636

Text #6

Max Range: 0.3536. Min Range: -0.3536

Max Act: 0.3265. Min Act: -0.0000

Data Index: 951678 (C4 (Web Text))

Max Activating Token Index: 798

Text #7

Max Range: 0.3536. Min Range: -0.3536

Max Act: 0.2943. Min Act: -0.0000

Data Index: 74216 (C4 (Web Text))

Max Activating Token Index: 987

Text #8

Max Range: 0.3536. Min Range: -0.3536

Max Act: 0.2925. Min Act: -0.0000

Data Index: 984044 (C4 (Web Text))

Max Activating Token Index: 1010

Text #9

Max Range: 0.3536. Min Range: -0.3536

Max Act: 0.2815. Min Act: -0.0000

Data Index: 159150 (C4 (Web Text))

Max Activating Token Index: 612

Text #10

Max Range: 0.3536. Min Range: -0.3536

Max Act: 0.2918. Min Act: -0.0000

Data Index: 933923 (C4 (Web Text))

Max Activating Token Index: 685

Text #11

Max Range: 0.3536. Min Range: -0.3536

Max Act: 0.2832. Min Act: -0.0000

Data Index: 568284 (C4 (Web Text))

Max Activating Token Index: 463

Text #12

Max Range: 0.3536. Min Range: -0.3536

Max Act: 0.2845. Min Act: 0.0000

Data Index: 905108 (C4 (Web Text))

Max Activating Token Index: 335

Text #13

Max Range: 0.3536. Min Range: -0.3536

Max Act: 0.2722. Min Act: -0.0000

Data Index: 127350 (C4 (Web Text))

Max Activating Token Index: 146

Text #14

Max Range: 0.3536. Min Range: -0.3536

Max Act: 0.2716. Min Act: -0.0000

Data Index: 491085 (C4 (Web Text))

Max Activating Token Index: 425

Text #15

Max Range: 0.3536. Min Range: -0.3536

Max Act: 0.2791. Min Act: -0.0000

Data Index: 1178676 (C4 (Web Text))

Max Activating Token Index: 379

Text #16

Max Range: 0.3536. Min Range: -0.3536

Max Act: 0.2688. Min Act: -0.0000

Data Index: 779964 (C4 (Web Text))

Max Activating Token Index: 125

Text #17

Max Range: 0.3536. Min Range: -0.3536

Max Act: 0.2588. Min Act: -0.0000

Data Index: 712915 (C4 (Web Text))

Max Activating Token Index: 703

Text #18

Max Range: 0.3536. Min Range: -0.3536

Max Act: 0.2602. Min Act: -0.0000

Data Index: 1336058 (C4 (Web Text))

Max Activating Token Index: 430

Text #19

Max Range: 0.3536. Min Range: -0.3536

Max Act: 0.2659. Min Act: -0.0000

Data Index: 1235058 (C4 (Web Text))

Max Activating Token Index: 113