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

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

Neuron 1736 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6143. Min Range: -0.6143

Max Act: 0.5745. Min Act: -0.0000

Data Index: 1385221 (Python Code)

Max Activating Token Index: 362

Text #1

Max Range: 0.6143. Min Range: -0.6143

Max Act: 0.5912. Min Act: -0.0000

Data Index: 1490542 (Python Code)

Max Activating Token Index: 135

Text #2

Max Range: 0.6143. Min Range: -0.6143

Max Act: 0.5878. Min Act: -0.0000

Data Index: 1152720 (C4 (Web Text))

Max Activating Token Index: 965

Text #3

Max Range: 0.6143. Min Range: -0.6143

Max Act: 0.6143. Min Act: -0.0000

Data Index: 1407398 (Python Code)

Max Activating Token Index: 116

Text #4

Max Range: 0.6143. Min Range: -0.6143

Max Act: 0.5616. Min Act: -0.0000

Data Index: 1617690 (Python Code)

Max Activating Token Index: 24

Text #5

Max Range: 0.6143. Min Range: -0.6143

Max Act: 0.5602. Min Act: -0.0000

Data Index: 493907 (C4 (Web Text))

Max Activating Token Index: 922

Text #6

Max Range: 0.6143. Min Range: -0.6143

Max Act: 0.5199. Min Act: -0.0000

Data Index: 1395772 (Python Code)

Max Activating Token Index: 19

Text #7

Max Range: 0.6143. Min Range: -0.6143

Max Act: 0.5344. Min Act: -0.0000

Data Index: 573713 (C4 (Web Text))

Max Activating Token Index: 343

Text #8

Max Range: 0.6143. Min Range: -0.6143

Max Act: 0.5300. Min Act: -0.0000

Data Index: 546403 (C4 (Web Text))

Max Activating Token Index: 168

Text #9

Max Range: 0.6143. Min Range: -0.6143

Max Act: 0.5297. Min Act: -0.0000

Data Index: 327946 (C4 (Web Text))

Max Activating Token Index: 29

Text #10

Max Range: 0.6143. Min Range: -0.6143

Max Act: 0.5480. Min Act: -0.0000

Data Index: 1395914 (Python Code)

Max Activating Token Index: 575

Text #11

Max Range: 0.6143. Min Range: -0.6143

Max Act: 0.4741. Min Act: -0.0000

Data Index: 1220634 (C4 (Web Text))

Max Activating Token Index: 784

Text #12

Max Range: 0.6143. Min Range: -0.6143

Max Act: 0.5243. Min Act: -0.0000

Data Index: 1563481 (Python Code)

Max Activating Token Index: 868

Text #13

Max Range: 0.6143. Min Range: -0.6143

Max Act: 0.5345. Min Act: -0.0000

Data Index: 1589277 (Python Code)

Max Activating Token Index: 681

Text #14

Max Range: 0.6143. Min Range: -0.6143

Max Act: 0.5174. Min Act: -0.0000

Data Index: 1509076 (Python Code)

Max Activating Token Index: 150

Text #15

Max Range: 0.6143. Min Range: -0.6143

Max Act: 0.5136. Min Act: -0.0000

Data Index: 1538266 (Python Code)

Max Activating Token Index: 652

Text #16

Max Range: 0.6143. Min Range: -0.6143

Max Act: 0.4972. Min Act: -0.0000

Data Index: 329868 (C4 (Web Text))

Max Activating Token Index: 629

Text #17

Max Range: 0.6143. Min Range: -0.6143

Max Act: 0.5151. Min Act: -0.0000

Data Index: 374121 (C4 (Web Text))

Max Activating Token Index: 389

Text #18

Max Range: 0.6143. Min Range: -0.6143

Max Act: 0.5222. Min Act: -0.0000

Data Index: 1592110 (Python Code)

Max Activating Token Index: 157

Text #19

Max Range: 0.6143. Min Range: -0.6143

Max Act: 0.4775. Min Act: -0.0000

Data Index: 1477363 (Python Code)

Max Activating Token Index: 98