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

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

Neuron 4886 in Layer 1

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: 0.8521. Min Range: -0.8521

Max Act: 0.8521. Min Act: -0.0002

Data Index: 240144 (C4 (Web Text))

Max Activating Token Index: 14

Text #1

Max Range: 0.8521. Min Range: -0.8521

Max Act: 0.8469. Min Act: -0.0002

Data Index: 387312 (C4 (Web Text))

Max Activating Token Index: 2

Text #2

Max Range: 0.8521. Min Range: -0.8521

Max Act: 0.8469. Min Act: -0.0002

Data Index: 1287726 (C4 (Web Text))

Max Activating Token Index: 2

Text #3

Max Range: 0.8521. Min Range: -0.8521

Max Act: 0.8153. Min Act: -0.0002

Data Index: 741477 (C4 (Web Text))

Max Activating Token Index: 247

Text #4

Max Range: 0.8521. Min Range: -0.8521

Max Act: 0.7999. Min Act: -0.0003

Data Index: 652459 (C4 (Web Text))

Max Activating Token Index: 39

Text #5

Max Range: 0.8521. Min Range: -0.8521

Max Act: 0.7958. Min Act: -0.0002

Data Index: 784923 (C4 (Web Text))

Max Activating Token Index: 49

Text #6

Max Range: 0.8521. Min Range: -0.8521

Max Act: 0.7911. Min Act: -0.0002

Data Index: 626162 (C4 (Web Text))

Max Activating Token Index: 15

Text #7

Max Range: 0.8521. Min Range: -0.8521

Max Act: 0.7785. Min Act: -0.0002

Data Index: 364144 (C4 (Web Text))

Max Activating Token Index: 54

Text #8

Max Range: 0.8521. Min Range: -0.8521

Max Act: 0.7583. Min Act: -0.0002

Data Index: 371708 (C4 (Web Text))

Max Activating Token Index: 88

Text #9

Max Range: 0.8521. Min Range: -0.8521

Max Act: 0.7756. Min Act: -0.0002

Data Index: 1069751 (C4 (Web Text))

Max Activating Token Index: 106

Text #10

Max Range: 0.8521. Min Range: -0.8521

Max Act: 0.7670. Min Act: -0.0002

Data Index: 843098 (C4 (Web Text))

Max Activating Token Index: 35

Text #11

Max Range: 0.8521. Min Range: -0.8521

Max Act: 0.7623. Min Act: -0.0002

Data Index: 143738 (C4 (Web Text))

Max Activating Token Index: 32

Text #12

Max Range: 0.8521. Min Range: -0.8521

Max Act: 0.7604. Min Act: -0.0002

Data Index: 151953 (C4 (Web Text))

Max Activating Token Index: 668

Text #13

Max Range: 0.8521. Min Range: -0.8521

Max Act: 0.7505. Min Act: -0.0002

Data Index: 1072740 (C4 (Web Text))

Max Activating Token Index: 52

Text #14

Max Range: 0.8521. Min Range: -0.8521

Max Act: 0.7389. Min Act: -0.0002

Data Index: 287234 (C4 (Web Text))

Max Activating Token Index: 5

Text #15

Max Range: 0.8521. Min Range: -0.8521

Max Act: 0.7518. Min Act: -0.0002

Data Index: 12851 (C4 (Web Text))

Max Activating Token Index: 28

Text #16

Max Range: 0.8521. Min Range: -0.8521

Max Act: 0.7334. Min Act: -0.0002

Data Index: 1343496 (C4 (Web Text))

Max Activating Token Index: 110

Text #17

Max Range: 0.8521. Min Range: -0.8521

Max Act: 0.7409. Min Act: -0.0002

Data Index: 243633 (C4 (Web Text))

Max Activating Token Index: 969

Text #18

Max Range: 0.8521. Min Range: -0.8521

Max Act: 0.7538. Min Act: -0.0002

Data Index: 699512 (C4 (Web Text))

Max Activating Token Index: 99

Text #19

Max Range: 0.8521. Min Range: -0.8521

Max Act: 0.7312. Min Act: -0.0003

Data Index: 98362 (C4 (Web Text))

Max Activating Token Index: 462