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

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

Neuron 2112 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: 0.0956. Min Range: -0.0956

Max Act: 0.0956. Min Act: -0.0002

Data Index: 1258033 (C4 (Web Text))

Max Activating Token Index: 76

Text #1

Max Range: 0.0956. Min Range: -0.0956

Max Act: 0.0730. Min Act: -0.0002

Data Index: 992985 (C4 (Web Text))

Max Activating Token Index: 213

Text #2

Max Range: 0.0956. Min Range: -0.0956

Max Act: 0.0737. Min Act: -0.0002

Data Index: 476951 (C4 (Web Text))

Max Activating Token Index: 104

Text #3

Max Range: 0.0956. Min Range: -0.0956

Max Act: 0.0720. Min Act: -0.0002

Data Index: 584496 (C4 (Web Text))

Max Activating Token Index: 312

Text #4

Max Range: 0.0956. Min Range: -0.0956

Max Act: 0.0707. Min Act: -0.0002

Data Index: 1349426 (C4 (Web Text))

Max Activating Token Index: 134

Text #5

Max Range: 0.0956. Min Range: -0.0956

Max Act: 0.0693. Min Act: -0.0002

Data Index: 1012481 (C4 (Web Text))

Max Activating Token Index: 81

Text #6

Max Range: 0.0956. Min Range: -0.0956

Max Act: 0.0683. Min Act: -0.0002

Data Index: 19526 (C4 (Web Text))

Max Activating Token Index: 847

Text #7

Max Range: 0.0956. Min Range: -0.0956

Max Act: 0.0690. Min Act: -0.0002

Data Index: 674218 (C4 (Web Text))

Max Activating Token Index: 106

Text #8

Max Range: 0.0956. Min Range: -0.0956

Max Act: 0.0641. Min Act: -0.0002

Data Index: 41392 (C4 (Web Text))

Max Activating Token Index: 159

Text #9

Max Range: 0.0956. Min Range: -0.0956

Max Act: 0.0638. Min Act: -0.0002

Data Index: 1081049 (C4 (Web Text))

Max Activating Token Index: 601

Text #10

Max Range: 0.0956. Min Range: -0.0956

Max Act: 0.0630. Min Act: -0.0002

Data Index: 161741 (C4 (Web Text))

Max Activating Token Index: 289

Text #11

Max Range: 0.0956. Min Range: -0.0956

Max Act: 0.0634. Min Act: -0.0003

Data Index: 1069791 (C4 (Web Text))

Max Activating Token Index: 65

Text #12

Max Range: 0.0956. Min Range: -0.0956

Max Act: 0.0625. Min Act: -0.0002

Data Index: 53414 (C4 (Web Text))

Max Activating Token Index: 627

Text #13

Max Range: 0.0956. Min Range: -0.0956

Max Act: 0.0611. Min Act: -0.0002

Data Index: 975820 (C4 (Web Text))

Max Activating Token Index: 414

Text #14

Max Range: 0.0956. Min Range: -0.0956

Max Act: 0.0598. Min Act: -0.0002

Data Index: 461826 (C4 (Web Text))

Max Activating Token Index: 498

Text #15

Max Range: 0.0956. Min Range: -0.0956

Max Act: 0.0617. Min Act: -0.0002

Data Index: 13314 (C4 (Web Text))

Max Activating Token Index: 193

Text #16

Max Range: 0.0956. Min Range: -0.0956

Max Act: 0.0588. Min Act: -0.0002

Data Index: 395371 (C4 (Web Text))

Max Activating Token Index: 956

Text #17

Max Range: 0.0956. Min Range: -0.0956

Max Act: 0.0584. Min Act: -0.0002

Data Index: 227687 (C4 (Web Text))

Max Activating Token Index: 967

Text #18

Max Range: 0.0956. Min Range: -0.0956

Max Act: 0.0610. Min Act: -0.0002

Data Index: 1230355 (C4 (Web Text))

Max Activating Token Index: 130

Text #19

Max Range: 0.0956. Min Range: -0.0956

Max Act: 0.0593. Min Act: -0.0002

Data Index: 776407 (C4 (Web Text))

Max Activating Token Index: 712