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

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

Neuron 4696 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: 0.5844. Min Range: -0.5844

Max Act: 0.5844. Min Act: -0.0002

Data Index: 1562986 (Python Code)

Max Activating Token Index: 3

Text #1

Max Range: 0.5844. Min Range: -0.5844

Max Act: 0.5738. Min Act: -0.0001

Data Index: 1397886 (Python Code)

Max Activating Token Index: 3

Text #2

Max Range: 0.5844. Min Range: -0.5844

Max Act: 0.5433. Min Act: -0.0001

Data Index: 562262 (C4 (Web Text))

Max Activating Token Index: 670

Text #3

Max Range: 0.5844. Min Range: -0.5844

Max Act: 0.5307. Min Act: -0.0001

Data Index: 181189 (C4 (Web Text))

Max Activating Token Index: 2

Text #4

Max Range: 0.5844. Min Range: -0.5844

Max Act: 0.5307. Min Act: -0.0001

Data Index: 1559095 (Python Code)

Max Activating Token Index: 6

Text #5

Max Range: 0.5844. Min Range: -0.5844

Max Act: 0.5086. Min Act: -0.0001

Data Index: 1433944 (Python Code)

Max Activating Token Index: 249

Text #6

Max Range: 0.5844. Min Range: -0.5844

Max Act: 0.5048. Min Act: -0.0001

Data Index: 88613 (C4 (Web Text))

Max Activating Token Index: 78

Text #7

Max Range: 0.5844. Min Range: -0.5844

Max Act: 0.4982. Min Act: -0.0001

Data Index: 563350 (C4 (Web Text))

Max Activating Token Index: 3

Text #8

Max Range: 0.5844. Min Range: -0.5844

Max Act: 0.4966. Min Act: -0.0001

Data Index: 1014559 (C4 (Web Text))

Max Activating Token Index: 714

Text #9

Max Range: 0.5844. Min Range: -0.5844

Max Act: 0.4986. Min Act: -0.0001

Data Index: 86065 (C4 (Web Text))

Max Activating Token Index: 169

Text #10

Max Range: 0.5844. Min Range: -0.5844

Max Act: 0.4881. Min Act: -0.0001

Data Index: 699522 (C4 (Web Text))

Max Activating Token Index: 223

Text #11

Max Range: 0.5844. Min Range: -0.5844

Max Act: 0.4854. Min Act: -0.0001

Data Index: 1637398 (Python Code)

Max Activating Token Index: 4

Text #12

Max Range: 0.5844. Min Range: -0.5844

Max Act: 0.4854. Min Act: -0.0001

Data Index: 1533341 (Python Code)

Max Activating Token Index: 4

Text #13

Max Range: 0.5844. Min Range: -0.5844

Max Act: 0.4913. Min Act: -0.0001

Data Index: 1239335 (C4 (Web Text))

Max Activating Token Index: 42

Text #14

Max Range: 0.5844. Min Range: -0.5844

Max Act: 0.4966. Min Act: -0.0001

Data Index: 301422 (C4 (Web Text))

Max Activating Token Index: 857

Text #15

Max Range: 0.5844. Min Range: -0.5844

Max Act: 0.5037. Min Act: -0.0001

Data Index: 755756 (C4 (Web Text))

Max Activating Token Index: 802

Text #16

Max Range: 0.5844. Min Range: -0.5844

Max Act: 0.4883. Min Act: -0.0001

Data Index: 301734 (C4 (Web Text))

Max Activating Token Index: 20

Text #17

Max Range: 0.5844. Min Range: -0.5844

Max Act: 0.4839. Min Act: -0.0001

Data Index: 1438089 (Python Code)

Max Activating Token Index: 179

Text #18

Max Range: 0.5844. Min Range: -0.5844

Max Act: 0.4851. Min Act: -0.0001

Data Index: 1245410 (C4 (Web Text))

Max Activating Token Index: 14

Text #19

Max Range: 0.5844. Min Range: -0.5844

Max Act: 0.4861. Min Act: -0.0001

Data Index: 676433 (C4 (Web Text))

Max Activating Token Index: 938