Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 934 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0528. Min Act: -0.0005

Data Index: 1035667 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0559. Min Act: -0.0005

Data Index: 1593091 (Python Code)

Max Activating Token Index: 1023

Text #2

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0505. Min Act: -0.0005

Data Index: 1556515 (Python Code)

Max Activating Token Index: 1023

Text #3

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0517. Min Act: -0.0005

Data Index: 180384 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0522. Min Act: -0.0005

Data Index: 309892 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0509. Min Act: -0.0005

Data Index: 33639 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0509. Min Act: -0.0005

Data Index: 1156517 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0489. Min Act: -0.0005

Data Index: 1449788 (Python Code)

Max Activating Token Index: 1023

Text #8

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0531. Min Act: -0.0005

Data Index: 125329 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0497. Min Act: -0.0005

Data Index: 1473032 (Python Code)

Max Activating Token Index: 1023

Text #10

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0535. Min Act: -0.0005

Data Index: 1605935 (Python Code)

Max Activating Token Index: 1023

Text #11

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0484. Min Act: -0.0005

Data Index: 662684 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0502. Min Act: -0.0005

Data Index: 976724 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0495. Min Act: -0.0005

Data Index: 1470089 (Python Code)

Max Activating Token Index: 1023

Text #14

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0486. Min Act: -0.0005

Data Index: 1277167 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0493. Min Act: -0.0005

Data Index: 1273317 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0493. Min Act: -0.0005

Data Index: 1504108 (Python Code)

Max Activating Token Index: 1023

Text #17

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0545. Min Act: -0.0005

Data Index: 340523 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0464. Min Act: -0.0005

Data Index: 1236311 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0482. Min Act: -0.0005

Data Index: 425240 (C4 (Web Text))

Max Activating Token Index: 1023