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

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

Neuron 2683 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.1362. Min Act: -0.0002

Data Index: 813762 (C4 (Web Text))

Max Activating Token Index: 881

Text #1

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.1367. Min Act: -0.0002

Data Index: 1309739 (C4 (Web Text))

Max Activating Token Index: 648

Text #2

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.1237. Min Act: -0.0002

Data Index: 1149770 (C4 (Web Text))

Max Activating Token Index: 772

Text #3

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.1248. Min Act: -0.0002

Data Index: 903707 (C4 (Web Text))

Max Activating Token Index: 510

Text #4

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.1216. Min Act: -0.0002

Data Index: 1327107 (C4 (Web Text))

Max Activating Token Index: 720

Text #5

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.1170. Min Act: -0.0002

Data Index: 166313 (C4 (Web Text))

Max Activating Token Index: 623

Text #6

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.1083. Min Act: -0.0002

Data Index: 662727 (C4 (Web Text))

Max Activating Token Index: 614

Text #7

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.1023. Min Act: -0.0002

Data Index: 964356 (C4 (Web Text))

Max Activating Token Index: 463

Text #8

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.1018. Min Act: -0.0002

Data Index: 1262378 (C4 (Web Text))

Max Activating Token Index: 839

Text #9

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.1008. Min Act: -0.0002

Data Index: 1234605 (C4 (Web Text))

Max Activating Token Index: 469

Text #10

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.0912. Min Act: -0.0002

Data Index: 412537 (C4 (Web Text))

Max Activating Token Index: 668

Text #11

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.0945. Min Act: -0.0002

Data Index: 178164 (C4 (Web Text))

Max Activating Token Index: 234

Text #12

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.0973. Min Act: -0.0002

Data Index: 585259 (C4 (Web Text))

Max Activating Token Index: 170

Text #13

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.0969. Min Act: -0.0002

Data Index: 1135770 (C4 (Web Text))

Max Activating Token Index: 593

Text #14

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.0921. Min Act: -0.0002

Data Index: 132603 (C4 (Web Text))

Max Activating Token Index: 574

Text #15

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.0977. Min Act: -0.0002

Data Index: 12323 (C4 (Web Text))

Max Activating Token Index: 278

Text #16

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.0947. Min Act: -0.0002

Data Index: 285671 (C4 (Web Text))

Max Activating Token Index: 544

Text #17

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.0899. Min Act: -0.0002

Data Index: 668964 (C4 (Web Text))

Max Activating Token Index: 858

Text #18

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.0866. Min Act: -0.0002

Data Index: 70561 (C4 (Web Text))

Max Activating Token Index: 412

Text #19

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.0828. Min Act: -0.0002

Data Index: 687858 (C4 (Web Text))

Max Activating Token Index: 878