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

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

Neuron 1030 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1348. Min Range: -1.1348

Max Act: 1.1348. Min Act: -0.0000

Data Index: 1201487 (C4 (Web Text))

Max Activating Token Index: 143

Text #1

Max Range: 1.1348. Min Range: -1.1348

Max Act: 1.0399. Min Act: -0.0000

Data Index: 792535 (C4 (Web Text))

Max Activating Token Index: 61

Text #2

Max Range: 1.1348. Min Range: -1.1348

Max Act: 1.0674. Min Act: -0.0000

Data Index: 593777 (C4 (Web Text))

Max Activating Token Index: 752

Text #3

Max Range: 1.1348. Min Range: -1.1348

Max Act: 1.0558. Min Act: -0.0000

Data Index: 1581578 (Python Code)

Max Activating Token Index: 855

Text #4

Max Range: 1.1348. Min Range: -1.1348

Max Act: 1.0059. Min Act: -0.0000

Data Index: 1558279 (Python Code)

Max Activating Token Index: 933

Text #5

Max Range: 1.1348. Min Range: -1.1348

Max Act: 0.8580. Min Act: -0.0000

Data Index: 1586421 (Python Code)

Max Activating Token Index: 786

Text #6

Max Range: 1.1348. Min Range: -1.1348

Max Act: 0.8963. Min Act: -0.0000

Data Index: 1508456 (Python Code)

Max Activating Token Index: 622

Text #7

Max Range: 1.1348. Min Range: -1.1348

Max Act: 1.0071. Min Act: -0.0000

Data Index: 500167 (C4 (Web Text))

Max Activating Token Index: 498

Text #8

Max Range: 1.1348. Min Range: -1.1348

Max Act: 1.0682. Min Act: -0.0000

Data Index: 252346 (C4 (Web Text))

Max Activating Token Index: 436

Text #9

Max Range: 1.1348. Min Range: -1.1348

Max Act: 0.9043. Min Act: -0.0000

Data Index: 802197 (C4 (Web Text))

Max Activating Token Index: 79

Text #10

Max Range: 1.1348. Min Range: -1.1348

Max Act: 0.9083. Min Act: -0.0000

Data Index: 1547268 (Python Code)

Max Activating Token Index: 780

Text #11

Max Range: 1.1348. Min Range: -1.1348

Max Act: 0.9161. Min Act: -0.0000

Data Index: 1446463 (Python Code)

Max Activating Token Index: 918

Text #12

Max Range: 1.1348. Min Range: -1.1348

Max Act: 0.9473. Min Act: -0.0000

Data Index: 1404383 (Python Code)

Max Activating Token Index: 782

Text #13

Max Range: 1.1348. Min Range: -1.1348

Max Act: 0.9795. Min Act: -0.0000

Data Index: 1542062 (Python Code)

Max Activating Token Index: 879

Text #14

Max Range: 1.1348. Min Range: -1.1348

Max Act: 0.9751. Min Act: -0.0000

Data Index: 526290 (C4 (Web Text))

Max Activating Token Index: 995

Text #15

Max Range: 1.1348. Min Range: -1.1348

Max Act: 1.0274. Min Act: -0.0000

Data Index: 1394961 (Python Code)

Max Activating Token Index: 948

Text #16

Max Range: 1.1348. Min Range: -1.1348

Max Act: 0.9586. Min Act: -0.0000

Data Index: 201697 (C4 (Web Text))

Max Activating Token Index: 622

Text #17

Max Range: 1.1348. Min Range: -1.1348

Max Act: 0.8742. Min Act: -0.0000

Data Index: 1547206 (Python Code)

Max Activating Token Index: 791

Text #18

Max Range: 1.1348. Min Range: -1.1348

Max Act: 0.7931. Min Act: -0.0000

Data Index: 1646763 (Python Code)

Max Activating Token Index: 947

Text #19

Max Range: 1.1348. Min Range: -1.1348

Max Act: 1.0769. Min Act: -0.0000

Data Index: 766903 (C4 (Web Text))

Max Activating Token Index: 279