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

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

Neuron 2198 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1732. Min Range: -0.1732

Max Act: 0.1732. Min Act: -0.0001

Data Index: 1529385 (Python Code)

Max Activating Token Index: 938

Text #1

Max Range: 0.1732. Min Range: -0.1732

Max Act: 0.1443. Min Act: -0.0001

Data Index: 1344242 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.1732. Min Range: -0.1732

Max Act: 0.1347. Min Act: -0.0001

Data Index: 732565 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.1732. Min Range: -0.1732

Max Act: 0.0701. Min Act: -0.0001

Data Index: 1569812 (Python Code)

Max Activating Token Index: 971

Text #4

Max Range: 0.1732. Min Range: -0.1732

Max Act: 0.1209. Min Act: -0.0001

Data Index: 203325 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.1732. Min Range: -0.1732

Max Act: 0.1089. Min Act: -0.0001

Data Index: 325855 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.1732. Min Range: -0.1732

Max Act: 0.1081. Min Act: -0.0001

Data Index: 25749 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.1732. Min Range: -0.1732

Max Act: 0.1026. Min Act: -0.0001

Data Index: 1294168 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.1732. Min Range: -0.1732

Max Act: 0.1040. Min Act: -0.0001

Data Index: 545072 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.1732. Min Range: -0.1732

Max Act: 0.1032. Min Act: -0.0001

Data Index: 569107 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.1732. Min Range: -0.1732

Max Act: 0.1012. Min Act: -0.0001

Data Index: 637708 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.1732. Min Range: -0.1732

Max Act: 0.1086. Min Act: -0.0001

Data Index: 4289 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.1732. Min Range: -0.1732

Max Act: 0.0998. Min Act: -0.0001

Data Index: 51327 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.1732. Min Range: -0.1732

Max Act: 0.0894. Min Act: -0.0001

Data Index: 347619 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.1732. Min Range: -0.1732

Max Act: 0.1086. Min Act: -0.0001

Data Index: 163702 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.1732. Min Range: -0.1732

Max Act: 0.0796. Min Act: -0.0001

Data Index: 1326609 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.1732. Min Range: -0.1732

Max Act: 0.0761. Min Act: -0.0001

Data Index: 1440739 (Python Code)

Max Activating Token Index: 1023

Text #17

Max Range: 0.1732. Min Range: -0.1732

Max Act: 0.0772. Min Act: -0.0001

Data Index: 1048657 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.1732. Min Range: -0.1732

Max Act: 0.0714. Min Act: -0.0001

Data Index: 1505449 (Python Code)

Max Activating Token Index: 688

Text #19

Max Range: 0.1732. Min Range: -0.1732

Max Act: 0.0765. Min Act: -0.0001

Data Index: 598205 (C4 (Web Text))

Max Activating Token Index: 1023