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

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

Neuron 1504 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: 0.0708. Min Range: -0.0708

Max Act: 0.0708. Min Act: -0.0002

Data Index: 1098219 (C4 (Web Text))

Max Activating Token Index: 127

Text #1

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0622. Min Act: -0.0002

Data Index: 244449 (C4 (Web Text))

Max Activating Token Index: 956

Text #2

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0611. Min Act: -0.0002

Data Index: 146079 (C4 (Web Text))

Max Activating Token Index: 231

Text #3

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0612. Min Act: -0.0002

Data Index: 667240 (C4 (Web Text))

Max Activating Token Index: 756

Text #4

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0595. Min Act: -0.0002

Data Index: 1305596 (C4 (Web Text))

Max Activating Token Index: 314

Text #5

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0603. Min Act: -0.0002

Data Index: 80459 (C4 (Web Text))

Max Activating Token Index: 115

Text #6

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0576. Min Act: -0.0002

Data Index: 866311 (C4 (Web Text))

Max Activating Token Index: 206

Text #7

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0578. Min Act: -0.0002

Data Index: 360447 (C4 (Web Text))

Max Activating Token Index: 368

Text #8

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0580. Min Act: -0.0002

Data Index: 140259 (C4 (Web Text))

Max Activating Token Index: 743

Text #9

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0578. Min Act: -0.0002

Data Index: 890914 (C4 (Web Text))

Max Activating Token Index: 320

Text #10

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0580. Min Act: -0.0002

Data Index: 1102804 (C4 (Web Text))

Max Activating Token Index: 476

Text #11

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0567. Min Act: -0.0003

Data Index: 1276256 (C4 (Web Text))

Max Activating Token Index: 65

Text #12

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0585. Min Act: -0.0002

Data Index: 737082 (C4 (Web Text))

Max Activating Token Index: 540

Text #13

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0566. Min Act: -0.0002

Data Index: 420224 (C4 (Web Text))

Max Activating Token Index: 886

Text #14

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0569. Min Act: -0.0002

Data Index: 1052912 (C4 (Web Text))

Max Activating Token Index: 65

Text #15

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0561. Min Act: -0.0002

Data Index: 165530 (C4 (Web Text))

Max Activating Token Index: 867

Text #16

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0576. Min Act: -0.0002

Data Index: 754342 (C4 (Web Text))

Max Activating Token Index: 451

Text #17

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0560. Min Act: -0.0002

Data Index: 1256405 (C4 (Web Text))

Max Activating Token Index: 756

Text #18

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0555. Min Act: -0.0002

Data Index: 810349 (C4 (Web Text))

Max Activating Token Index: 26

Text #19

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0558. Min Act: -0.0002

Data Index: 641290 (C4 (Web Text))

Max Activating Token Index: 277