Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2291 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2631. Min Range: -0.2631

Max Act: 0.2631. Min Act: -0.0001

Data Index: 1022038 (C4 (Web Text))

Max Activating Token Index: 749

Text #1

Max Range: 0.2631. Min Range: -0.2631

Max Act: 0.2497. Min Act: -0.0000

Data Index: 604926 (C4 (Web Text))

Max Activating Token Index: 139

Text #2

Max Range: 0.2631. Min Range: -0.2631

Max Act: 0.2352. Min Act: -0.0000

Data Index: 362206 (C4 (Web Text))

Max Activating Token Index: 55

Text #3

Max Range: 0.2631. Min Range: -0.2631

Max Act: 0.2309. Min Act: -0.0001

Data Index: 708166 (C4 (Web Text))

Max Activating Token Index: 91

Text #4

Max Range: 0.2631. Min Range: -0.2631

Max Act: 0.2088. Min Act: -0.0001

Data Index: 1009652 (C4 (Web Text))

Max Activating Token Index: 619

Text #5

Max Range: 0.2631. Min Range: -0.2631

Max Act: 0.2140. Min Act: -0.0001

Data Index: 795173 (C4 (Web Text))

Max Activating Token Index: 327

Text #6

Max Range: 0.2631. Min Range: -0.2631

Max Act: 0.2076. Min Act: -0.0000

Data Index: 362897 (C4 (Web Text))

Max Activating Token Index: 1014

Text #7

Max Range: 0.2631. Min Range: -0.2631

Max Act: 0.2038. Min Act: -0.0001

Data Index: 615144 (C4 (Web Text))

Max Activating Token Index: 970

Text #8

Max Range: 0.2631. Min Range: -0.2631

Max Act: 0.1984. Min Act: -0.0001

Data Index: 1078075 (C4 (Web Text))

Max Activating Token Index: 26

Text #9

Max Range: 0.2631. Min Range: -0.2631

Max Act: 0.1882. Min Act: -0.0001

Data Index: 1576204 (Python Code)

Max Activating Token Index: 150

Text #10

Max Range: 0.2631. Min Range: -0.2631

Max Act: 0.1797. Min Act: -0.0001

Data Index: 814287 (C4 (Web Text))

Max Activating Token Index: 104

Text #11

Max Range: 0.2631. Min Range: -0.2631

Max Act: 0.1708. Min Act: -0.0000

Data Index: 1031573 (C4 (Web Text))

Max Activating Token Index: 362

Text #12

Max Range: 0.2631. Min Range: -0.2631

Max Act: 0.1727. Min Act: -0.0001

Data Index: 1341919 (C4 (Web Text))

Max Activating Token Index: 104

Text #13

Max Range: 0.2631. Min Range: -0.2631

Max Act: 0.1702. Min Act: -0.0001

Data Index: 185197 (C4 (Web Text))

Max Activating Token Index: 925

Text #14

Max Range: 0.2631. Min Range: -0.2631

Max Act: 0.1616. Min Act: -0.0000

Data Index: 784515 (C4 (Web Text))

Max Activating Token Index: 157

Text #15

Max Range: 0.2631. Min Range: -0.2631

Max Act: 0.1687. Min Act: -0.0001

Data Index: 784643 (C4 (Web Text))

Max Activating Token Index: 57

Text #16

Max Range: 0.2631. Min Range: -0.2631

Max Act: 0.1670. Min Act: -0.0000

Data Index: 818842 (C4 (Web Text))

Max Activating Token Index: 419

Text #17

Max Range: 0.2631. Min Range: -0.2631

Max Act: 0.1728. Min Act: -0.0001

Data Index: 1249723 (C4 (Web Text))

Max Activating Token Index: 330

Text #18

Max Range: 0.2631. Min Range: -0.2631

Max Act: 0.1665. Min Act: -0.0001

Data Index: 268760 (C4 (Web Text))

Max Activating Token Index: 297

Text #19

Max Range: 0.2631. Min Range: -0.2631

Max Act: 0.1540. Min Act: -0.0001

Data Index: 555195 (C4 (Web Text))

Max Activating Token Index: 879