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

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

Neuron 1492 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0861. Min Range: -3.0861

Max Act: 3.0861. Min Act: -0.0000

Data Index: 1072164 (C4 (Web Text))

Max Activating Token Index: 931

Text #1

Max Range: 3.0861. Min Range: -3.0861

Max Act: 2.5334. Min Act: -0.0000

Data Index: 1084959 (C4 (Web Text))

Max Activating Token Index: 720

Text #2

Max Range: 3.0861. Min Range: -3.0861

Max Act: 2.6364. Min Act: -0.0000

Data Index: 768165 (C4 (Web Text))

Max Activating Token Index: 767

Text #3

Max Range: 3.0861. Min Range: -3.0861

Max Act: 2.6256. Min Act: -0.0000

Data Index: 583236 (C4 (Web Text))

Max Activating Token Index: 112

Text #4

Max Range: 3.0861. Min Range: -3.0861

Max Act: 2.3442. Min Act: -0.0000

Data Index: 500875 (C4 (Web Text))

Max Activating Token Index: 85

Text #5

Max Range: 3.0861. Min Range: -3.0861

Max Act: 2.2991. Min Act: -0.0000

Data Index: 338794 (C4 (Web Text))

Max Activating Token Index: 175

Text #6

Max Range: 3.0861. Min Range: -3.0861

Max Act: 2.2761. Min Act: -0.0000

Data Index: 489917 (C4 (Web Text))

Max Activating Token Index: 884

Text #7

Max Range: 3.0861. Min Range: -3.0861

Max Act: 2.3813. Min Act: -0.0000

Data Index: 120871 (C4 (Web Text))

Max Activating Token Index: 55

Text #8

Max Range: 3.0861. Min Range: -3.0861

Max Act: 2.2224. Min Act: -0.0000

Data Index: 835643 (C4 (Web Text))

Max Activating Token Index: 183

Text #9

Max Range: 3.0861. Min Range: -3.0861

Max Act: 2.1761. Min Act: -0.0000

Data Index: 396565 (C4 (Web Text))

Max Activating Token Index: 291

Text #10

Max Range: 3.0861. Min Range: -3.0861

Max Act: 2.2782. Min Act: -0.0000

Data Index: 1328588 (C4 (Web Text))

Max Activating Token Index: 282

Text #11

Max Range: 3.0861. Min Range: -3.0861

Max Act: 2.1431. Min Act: -0.0000

Data Index: 1102029 (C4 (Web Text))

Max Activating Token Index: 467

Text #12

Max Range: 3.0861. Min Range: -3.0861

Max Act: 2.0206. Min Act: -0.0000

Data Index: 526331 (C4 (Web Text))

Max Activating Token Index: 29

Text #13

Max Range: 3.0861. Min Range: -3.0861

Max Act: 2.0639. Min Act: -0.0000

Data Index: 666896 (C4 (Web Text))

Max Activating Token Index: 645

Text #14

Max Range: 3.0861. Min Range: -3.0861

Max Act: 2.0353. Min Act: -0.0000

Data Index: 1076749 (C4 (Web Text))

Max Activating Token Index: 498

Text #15

Max Range: 3.0861. Min Range: -3.0861

Max Act: 2.1272. Min Act: -0.0000

Data Index: 546660 (C4 (Web Text))

Max Activating Token Index: 434

Text #16

Max Range: 3.0861. Min Range: -3.0861

Max Act: 2.0097. Min Act: -0.0000

Data Index: 754635 (C4 (Web Text))

Max Activating Token Index: 25

Text #17

Max Range: 3.0861. Min Range: -3.0861

Max Act: 1.9190. Min Act: -0.0000

Data Index: 1041177 (C4 (Web Text))

Max Activating Token Index: 800

Text #18

Max Range: 3.0861. Min Range: -3.0861

Max Act: 1.9926. Min Act: -0.0000

Data Index: 742282 (C4 (Web Text))

Max Activating Token Index: 898

Text #19

Max Range: 3.0861. Min Range: -3.0861

Max Act: 1.7709. Min Act: -0.0000

Data Index: 1130769 (C4 (Web Text))

Max Activating Token Index: 234