Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2455 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0535. Min Act: -0.0003

Data Index: 169945 (C4 (Web Text))

Max Activating Token Index: 360

Text #1

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0517. Min Act: -0.0003

Data Index: 907841 (C4 (Web Text))

Max Activating Token Index: 820

Text #2

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0521. Min Act: -0.0003

Data Index: 101424 (C4 (Web Text))

Max Activating Token Index: 975

Text #3

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0502. Min Act: -0.0003

Data Index: 57628 (C4 (Web Text))

Max Activating Token Index: 150

Text #4

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0498. Min Act: -0.0003

Data Index: 1579313 (Python Code)

Max Activating Token Index: 28

Text #5

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0517. Min Act: -0.0003

Data Index: 1000177 (C4 (Web Text))

Max Activating Token Index: 590

Text #6

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0484. Min Act: -0.0003

Data Index: 1037473 (C4 (Web Text))

Max Activating Token Index: 697

Text #7

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0474. Min Act: -0.0003

Data Index: 467473 (C4 (Web Text))

Max Activating Token Index: 644

Text #8

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0447. Min Act: -0.0003

Data Index: 245467 (C4 (Web Text))

Max Activating Token Index: 825

Text #9

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0449. Min Act: -0.0003

Data Index: 985322 (C4 (Web Text))

Max Activating Token Index: 640

Text #10

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0445. Min Act: -0.0003

Data Index: 176677 (C4 (Web Text))

Max Activating Token Index: 135

Text #11

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0461. Min Act: -0.0003

Data Index: 1510755 (Python Code)

Max Activating Token Index: 21

Text #12

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0461. Min Act: -0.0003

Data Index: 791973 (C4 (Web Text))

Max Activating Token Index: 569

Text #13

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0436. Min Act: -0.0003

Data Index: 1179270 (C4 (Web Text))

Max Activating Token Index: 325

Text #14

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0430. Min Act: -0.0003

Data Index: 1379874 (Python Code)

Max Activating Token Index: 336

Text #15

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0463. Min Act: -0.0003

Data Index: 977717 (C4 (Web Text))

Max Activating Token Index: 165

Text #16

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0439. Min Act: -0.0003

Data Index: 975835 (C4 (Web Text))

Max Activating Token Index: 381

Text #17

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0456. Min Act: -0.0003

Data Index: 1109544 (C4 (Web Text))

Max Activating Token Index: 229

Text #18

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0466. Min Act: -0.0003

Data Index: 278189 (C4 (Web Text))

Max Activating Token Index: 174

Text #19

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0427. Min Act: -0.0003

Data Index: 594853 (C4 (Web Text))

Max Activating Token Index: 801