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

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

Neuron 2949 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0045. Min Range: -2.0045

Max Act: 1.9024. Min Act: -0.0000

Data Index: 135794 (C4 (Web Text))

Max Activating Token Index: 306

Text #1

Max Range: 2.0045. Min Range: -2.0045

Max Act: 1.9217. Min Act: -0.0000

Data Index: 1022819 (C4 (Web Text))

Max Activating Token Index: 418

Text #2

Max Range: 2.0045. Min Range: -2.0045

Max Act: 2.0045. Min Act: -0.0000

Data Index: 408802 (C4 (Web Text))

Max Activating Token Index: 418

Text #3

Max Range: 2.0045. Min Range: -2.0045

Max Act: 1.9916. Min Act: -0.0000

Data Index: 824543 (C4 (Web Text))

Max Activating Token Index: 332

Text #4

Max Range: 2.0045. Min Range: -2.0045

Max Act: 1.8307. Min Act: -0.0000

Data Index: 946884 (C4 (Web Text))

Max Activating Token Index: 885

Text #5

Max Range: 2.0045. Min Range: -2.0045

Max Act: 1.7653. Min Act: -0.0000

Data Index: 1049070 (C4 (Web Text))

Max Activating Token Index: 90

Text #6

Max Range: 2.0045. Min Range: -2.0045

Max Act: 1.7698. Min Act: -0.0000

Data Index: 147963 (C4 (Web Text))

Max Activating Token Index: 1016

Text #7

Max Range: 2.0045. Min Range: -2.0045

Max Act: 1.6670. Min Act: -0.0000

Data Index: 975502 (C4 (Web Text))

Max Activating Token Index: 306

Text #8

Max Range: 2.0045. Min Range: -2.0045

Max Act: 1.6585. Min Act: -0.0000

Data Index: 918538 (C4 (Web Text))

Max Activating Token Index: 338

Text #9

Max Range: 2.0045. Min Range: -2.0045

Max Act: 1.7571. Min Act: -0.0000

Data Index: 226447 (C4 (Web Text))

Max Activating Token Index: 488

Text #10

Max Range: 2.0045. Min Range: -2.0045

Max Act: 1.6128. Min Act: -0.0000

Data Index: 450005 (C4 (Web Text))

Max Activating Token Index: 661

Text #11

Max Range: 2.0045. Min Range: -2.0045

Max Act: 1.7988. Min Act: -0.0000

Data Index: 562861 (C4 (Web Text))

Max Activating Token Index: 314

Text #12

Max Range: 2.0045. Min Range: -2.0045

Max Act: 1.5795. Min Act: -0.0000

Data Index: 178218 (C4 (Web Text))

Max Activating Token Index: 537

Text #13

Max Range: 2.0045. Min Range: -2.0045

Max Act: 1.5931. Min Act: -0.0000

Data Index: 276992 (C4 (Web Text))

Max Activating Token Index: 423

Text #14

Max Range: 2.0045. Min Range: -2.0045

Max Act: 1.7524. Min Act: -0.0000

Data Index: 272068 (C4 (Web Text))

Max Activating Token Index: 972

Text #15

Max Range: 2.0045. Min Range: -2.0045

Max Act: 1.7204. Min Act: -0.0000

Data Index: 507777 (C4 (Web Text))

Max Activating Token Index: 660

Text #16

Max Range: 2.0045. Min Range: -2.0045

Max Act: 1.4866. Min Act: -0.0000

Data Index: 289591 (C4 (Web Text))

Max Activating Token Index: 582

Text #17

Max Range: 2.0045. Min Range: -2.0045

Max Act: 1.5713. Min Act: -0.0000

Data Index: 1246066 (C4 (Web Text))

Max Activating Token Index: 76

Text #18

Max Range: 2.0045. Min Range: -2.0045

Max Act: 1.5390. Min Act: -0.0000

Data Index: 239425 (C4 (Web Text))

Max Activating Token Index: 494

Text #19

Max Range: 2.0045. Min Range: -2.0045

Max Act: 1.5132. Min Act: -0.0000

Data Index: 907241 (C4 (Web Text))

Max Activating Token Index: 495