Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4949 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0519. Min Act: -0.0001

Data Index: 888023 (C4 (Web Text))

Max Activating Token Index: 844

Text #1

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0492. Min Act: -0.0001

Data Index: 33168 (C4 (Web Text))

Max Activating Token Index: 962

Text #2

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0519. Min Act: -0.0001

Data Index: 73261 (C4 (Web Text))

Max Activating Token Index: 832

Text #3

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0481. Min Act: -0.0001

Data Index: 117709 (C4 (Web Text))

Max Activating Token Index: 357

Text #4

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0470. Min Act: -0.0001

Data Index: 1242307 (C4 (Web Text))

Max Activating Token Index: 29

Text #5

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0471. Min Act: -0.0001

Data Index: 487901 (C4 (Web Text))

Max Activating Token Index: 864

Text #6

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0462. Min Act: -0.0001

Data Index: 1190461 (C4 (Web Text))

Max Activating Token Index: 355

Text #7

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0426. Min Act: -0.0001

Data Index: 748722 (C4 (Web Text))

Max Activating Token Index: 901

Text #8

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0404. Min Act: -0.0000

Data Index: 1524729 (Python Code)

Max Activating Token Index: 810

Text #9

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0428. Min Act: -0.0001

Data Index: 1117441 (C4 (Web Text))

Max Activating Token Index: 955

Text #10

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0444. Min Act: -0.0001

Data Index: 370251 (C4 (Web Text))

Max Activating Token Index: 96

Text #11

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0390. Min Act: -0.0001

Data Index: 437688 (C4 (Web Text))

Max Activating Token Index: 800

Text #12

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0430. Min Act: -0.0001

Data Index: 423572 (C4 (Web Text))

Max Activating Token Index: 12

Text #13

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0442. Min Act: -0.0001

Data Index: 1607811 (Python Code)

Max Activating Token Index: 23

Text #14

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0451. Min Act: -0.0001

Data Index: 549158 (C4 (Web Text))

Max Activating Token Index: 165

Text #15

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0377. Min Act: -0.0001

Data Index: 900531 (C4 (Web Text))

Max Activating Token Index: 804

Text #16

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0418. Min Act: -0.0001

Data Index: 498003 (C4 (Web Text))

Max Activating Token Index: 355

Text #17

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0433. Min Act: -0.0001

Data Index: 412080 (C4 (Web Text))

Max Activating Token Index: 591

Text #18

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0422. Min Act: -0.0000

Data Index: 885812 (C4 (Web Text))

Max Activating Token Index: 531

Text #19

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0391. Min Act: -0.0001

Data Index: 917277 (C4 (Web Text))

Max Activating Token Index: 743