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

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

Neuron 3752 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0756. Min Act: -0.0001

Data Index: 1607933 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0657. Min Act: -0.0001

Data Index: 909114 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0650. Min Act: -0.0001

Data Index: 1453512 (Python Code)

Max Activating Token Index: 1023

Text #3

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0615. Min Act: -0.0001

Data Index: 1557031 (Python Code)

Max Activating Token Index: 1023

Text #4

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0626. Min Act: -0.0001

Data Index: 1617269 (Python Code)

Max Activating Token Index: 1023

Text #5

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0628. Min Act: -0.0001

Data Index: 892133 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0603. Min Act: -0.0001

Data Index: 760901 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0603. Min Act: -0.0001

Data Index: 421214 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0601. Min Act: -0.0001

Data Index: 958678 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0605. Min Act: -0.0001

Data Index: 1571726 (Python Code)

Max Activating Token Index: 1023

Text #10

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0585. Min Act: -0.0001

Data Index: 1348616 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0596. Min Act: -0.0001

Data Index: 1416270 (Python Code)

Max Activating Token Index: 1023

Text #12

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0591. Min Act: -0.0001

Data Index: 989286 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0592. Min Act: -0.0001

Data Index: 1547896 (Python Code)

Max Activating Token Index: 1023

Text #14

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0572. Min Act: -0.0001

Data Index: 258443 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0584. Min Act: -0.0001

Data Index: 1477929 (Python Code)

Max Activating Token Index: 1023

Text #16

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0575. Min Act: -0.0001

Data Index: 202758 (C4 (Web Text))

Max Activating Token Index: 153

Text #17

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0570. Min Act: -0.0001

Data Index: 875855 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0567. Min Act: -0.0001

Data Index: 1271736 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0565. Min Act: -0.0001

Data Index: 1278120 (C4 (Web Text))

Max Activating Token Index: 1023