Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2306 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.4746. Min Range: -0.4746

Max Act: 0.4464. Min Act: -0.0001

Data Index: 1140084 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.4746. Min Range: -0.4746

Max Act: 0.4746. Min Act: -0.0001

Data Index: 341280 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.4746. Min Range: -0.4746

Max Act: 0.4493. Min Act: -0.0001

Data Index: 1487683 (Python Code)

Max Activating Token Index: 1023

Text #3

Max Range: 0.4746. Min Range: -0.4746

Max Act: 0.4324. Min Act: -0.0001

Data Index: 836504 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.4746. Min Range: -0.4746

Max Act: 0.4254. Min Act: -0.0001

Data Index: 1651307 (Python Code)

Max Activating Token Index: 1023

Text #5

Max Range: 0.4746. Min Range: -0.4746

Max Act: 0.3745. Min Act: -0.0001

Data Index: 1189127 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.4746. Min Range: -0.4746

Max Act: 0.3987. Min Act: -0.0001

Data Index: 506714 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.4746. Min Range: -0.4746

Max Act: 0.3975. Min Act: -0.0001

Data Index: 1581015 (Python Code)

Max Activating Token Index: 1023

Text #8

Max Range: 0.4746. Min Range: -0.4746

Max Act: 0.3762. Min Act: -0.0001

Data Index: 1636545 (Python Code)

Max Activating Token Index: 1023

Text #9

Max Range: 0.4746. Min Range: -0.4746

Max Act: 0.3761. Min Act: -0.0001

Data Index: 1430284 (Python Code)

Max Activating Token Index: 1023

Text #10

Max Range: 0.4746. Min Range: -0.4746

Max Act: 0.3899. Min Act: -0.0001

Data Index: 1463630 (Python Code)

Max Activating Token Index: 1023

Text #11

Max Range: 0.4746. Min Range: -0.4746

Max Act: 0.3883. Min Act: -0.0001

Data Index: 983883 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.4746. Min Range: -0.4746

Max Act: 0.3460. Min Act: -0.0001

Data Index: 15495 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.4746. Min Range: -0.4746

Max Act: 0.3951. Min Act: -0.0001

Data Index: 1144523 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.4746. Min Range: -0.4746

Max Act: 0.3653. Min Act: -0.0001

Data Index: 1394423 (Python Code)

Max Activating Token Index: 1023

Text #15

Max Range: 0.4746. Min Range: -0.4746

Max Act: 0.3768. Min Act: -0.0001

Data Index: 590265 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.4746. Min Range: -0.4746

Max Act: 0.3840. Min Act: -0.0001

Data Index: 1576139 (Python Code)

Max Activating Token Index: 1023

Text #17

Max Range: 0.4746. Min Range: -0.4746

Max Act: 0.3717. Min Act: -0.0001

Data Index: 18144 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.4746. Min Range: -0.4746

Max Act: 0.3688. Min Act: -0.0001

Data Index: 1567941 (Python Code)

Max Activating Token Index: 1023

Text #19

Max Range: 0.4746. Min Range: -0.4746

Max Act: 0.3678. Min Act: -0.0001

Data Index: 1431220 (Python Code)

Max Activating Token Index: 1023