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

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

Neuron 5066 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.2658. Min Range: -4.2658

Max Act: 4.2658. Min Act: -0.0000

Data Index: 259498 (C4 (Web Text))

Max Activating Token Index: 390

Text #1

Max Range: 4.2658. Min Range: -4.2658

Max Act: 4.1063. Min Act: -0.0001

Data Index: 648992 (C4 (Web Text))

Max Activating Token Index: 696

Text #2

Max Range: 4.2658. Min Range: -4.2658

Max Act: 3.6668. Min Act: -0.0001

Data Index: 268097 (C4 (Web Text))

Max Activating Token Index: 978

Text #3

Max Range: 4.2658. Min Range: -4.2658

Max Act: 3.5710. Min Act: -0.0001

Data Index: 717447 (C4 (Web Text))

Max Activating Token Index: 147

Text #4

Max Range: 4.2658. Min Range: -4.2658

Max Act: 3.3185. Min Act: -0.0001

Data Index: 236862 (C4 (Web Text))

Max Activating Token Index: 73

Text #5

Max Range: 4.2658. Min Range: -4.2658

Max Act: 2.7732. Min Act: -0.0000

Data Index: 848330 (C4 (Web Text))

Max Activating Token Index: 392

Text #6

Max Range: 4.2658. Min Range: -4.2658

Max Act: 2.9146. Min Act: -0.0000

Data Index: 139329 (C4 (Web Text))

Max Activating Token Index: 121

Text #7

Max Range: 4.2658. Min Range: -4.2658

Max Act: 2.7180. Min Act: -0.0001

Data Index: 160797 (C4 (Web Text))

Max Activating Token Index: 223

Text #8

Max Range: 4.2658. Min Range: -4.2658

Max Act: 2.4148. Min Act: -0.0000

Data Index: 1217443 (C4 (Web Text))

Max Activating Token Index: 171

Text #9

Max Range: 4.2658. Min Range: -4.2658

Max Act: 2.7682. Min Act: -0.0000

Data Index: 140940 (C4 (Web Text))

Max Activating Token Index: 718

Text #10

Max Range: 4.2658. Min Range: -4.2658

Max Act: 2.6314. Min Act: -0.0000

Data Index: 634398 (C4 (Web Text))

Max Activating Token Index: 765

Text #11

Max Range: 4.2658. Min Range: -4.2658

Max Act: 2.7524. Min Act: -0.0001

Data Index: 727209 (C4 (Web Text))

Max Activating Token Index: 850

Text #12

Max Range: 4.2658. Min Range: -4.2658

Max Act: 2.5027. Min Act: -0.0000

Data Index: 1116924 (C4 (Web Text))

Max Activating Token Index: 908

Text #13

Max Range: 4.2658. Min Range: -4.2658

Max Act: 2.4922. Min Act: -0.0001

Data Index: 12438 (C4 (Web Text))

Max Activating Token Index: 754

Text #14

Max Range: 4.2658. Min Range: -4.2658

Max Act: 2.5960. Min Act: -0.0000

Data Index: 1110847 (C4 (Web Text))

Max Activating Token Index: 26

Text #15

Max Range: 4.2658. Min Range: -4.2658

Max Act: 2.5726. Min Act: -0.0000

Data Index: 878050 (C4 (Web Text))

Max Activating Token Index: 588

Text #16

Max Range: 4.2658. Min Range: -4.2658

Max Act: 2.4561. Min Act: -0.0000

Data Index: 599695 (C4 (Web Text))

Max Activating Token Index: 796

Text #17

Max Range: 4.2658. Min Range: -4.2658

Max Act: 2.5849. Min Act: -0.0001

Data Index: 785664 (C4 (Web Text))

Max Activating Token Index: 691

Text #18

Max Range: 4.2658. Min Range: -4.2658

Max Act: 2.4006. Min Act: -0.0000

Data Index: 35336 (C4 (Web Text))

Max Activating Token Index: 330

Text #19

Max Range: 4.2658. Min Range: -4.2658

Max Act: 2.3718. Min Act: -0.0000

Data Index: 1131867 (C4 (Web Text))

Max Activating Token Index: 104