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

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

Neuron 4058 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: 0.4186. Min Range: -0.4186

Max Act: 0.4186. Min Act: -0.0002

Data Index: 693210 (C4 (Web Text))

Max Activating Token Index: 326

Text #1

Max Range: 0.4186. Min Range: -0.4186

Max Act: 0.4171. Min Act: -0.0002

Data Index: 1286908 (C4 (Web Text))

Max Activating Token Index: 6

Text #2

Max Range: 0.4186. Min Range: -0.4186

Max Act: 0.3937. Min Act: -0.0002

Data Index: 661565 (C4 (Web Text))

Max Activating Token Index: 46

Text #3

Max Range: 0.4186. Min Range: -0.4186

Max Act: 0.4002. Min Act: -0.0002

Data Index: 1156318 (C4 (Web Text))

Max Activating Token Index: 891

Text #4

Max Range: 0.4186. Min Range: -0.4186

Max Act: 0.3755. Min Act: -0.0002

Data Index: 1140401 (C4 (Web Text))

Max Activating Token Index: 88

Text #5

Max Range: 0.4186. Min Range: -0.4186

Max Act: 0.3825. Min Act: -0.0002

Data Index: 1311173 (C4 (Web Text))

Max Activating Token Index: 895

Text #6

Max Range: 0.4186. Min Range: -0.4186

Max Act: 0.3703. Min Act: -0.0002

Data Index: 24645 (C4 (Web Text))

Max Activating Token Index: 961

Text #7

Max Range: 0.4186. Min Range: -0.4186

Max Act: 0.3683. Min Act: -0.0002

Data Index: 627960 (C4 (Web Text))

Max Activating Token Index: 742

Text #8

Max Range: 0.4186. Min Range: -0.4186

Max Act: 0.3784. Min Act: -0.0002

Data Index: 518467 (C4 (Web Text))

Max Activating Token Index: 818

Text #9

Max Range: 0.4186. Min Range: -0.4186

Max Act: 0.3703. Min Act: -0.0002

Data Index: 527276 (C4 (Web Text))

Max Activating Token Index: 134

Text #10

Max Range: 0.4186. Min Range: -0.4186

Max Act: 0.3665. Min Act: -0.0002

Data Index: 1035254 (C4 (Web Text))

Max Activating Token Index: 137

Text #11

Max Range: 0.4186. Min Range: -0.4186

Max Act: 0.3632. Min Act: -0.0002

Data Index: 929667 (C4 (Web Text))

Max Activating Token Index: 936

Text #12

Max Range: 0.4186. Min Range: -0.4186

Max Act: 0.3646. Min Act: -0.0002

Data Index: 499019 (C4 (Web Text))

Max Activating Token Index: 880

Text #13

Max Range: 0.4186. Min Range: -0.4186

Max Act: 0.3649. Min Act: -0.0002

Data Index: 940916 (C4 (Web Text))

Max Activating Token Index: 44

Text #14

Max Range: 0.4186. Min Range: -0.4186

Max Act: 0.3677. Min Act: -0.0002

Data Index: 1303231 (C4 (Web Text))

Max Activating Token Index: 189

Text #15

Max Range: 0.4186. Min Range: -0.4186

Max Act: 0.3678. Min Act: -0.0002

Data Index: 1095589 (C4 (Web Text))

Max Activating Token Index: 780

Text #16

Max Range: 0.4186. Min Range: -0.4186

Max Act: 0.3601. Min Act: -0.0002

Data Index: 633215 (C4 (Web Text))

Max Activating Token Index: 230

Text #17

Max Range: 0.4186. Min Range: -0.4186

Max Act: 0.3585. Min Act: -0.0002

Data Index: 1093714 (C4 (Web Text))

Max Activating Token Index: 423

Text #18

Max Range: 0.4186. Min Range: -0.4186

Max Act: 0.3510. Min Act: -0.0002

Data Index: 799411 (C4 (Web Text))

Max Activating Token Index: 770

Text #19

Max Range: 0.4186. Min Range: -0.4186

Max Act: 0.3634. Min Act: -0.0002

Data Index: 965176 (C4 (Web Text))

Max Activating Token Index: 304