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

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

Neuron 2860 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3112. Min Range: -0.3112

Max Act: 0.3112. Min Act: -0.0000

Data Index: 373941 (C4 (Web Text))

Max Activating Token Index: 614

Text #1

Max Range: 0.3112. Min Range: -0.3112

Max Act: 0.2854. Min Act: -0.0000

Data Index: 334833 (C4 (Web Text))

Max Activating Token Index: 514

Text #2

Max Range: 0.3112. Min Range: -0.3112

Max Act: 0.2882. Min Act: -0.0000

Data Index: 1138508 (C4 (Web Text))

Max Activating Token Index: 121

Text #3

Max Range: 0.3112. Min Range: -0.3112

Max Act: 0.2791. Min Act: -0.0000

Data Index: 129769 (C4 (Web Text))

Max Activating Token Index: 954

Text #4

Max Range: 0.3112. Min Range: -0.3112

Max Act: 0.2770. Min Act: -0.0000

Data Index: 786165 (C4 (Web Text))

Max Activating Token Index: 834

Text #5

Max Range: 0.3112. Min Range: -0.3112

Max Act: 0.2848. Min Act: -0.0000

Data Index: 856047 (C4 (Web Text))

Max Activating Token Index: 256

Text #6

Max Range: 0.3112. Min Range: -0.3112

Max Act: 0.2641. Min Act: -0.0000

Data Index: 805603 (C4 (Web Text))

Max Activating Token Index: 232

Text #7

Max Range: 0.3112. Min Range: -0.3112

Max Act: 0.2621. Min Act: -0.0000

Data Index: 382808 (C4 (Web Text))

Max Activating Token Index: 882

Text #8

Max Range: 0.3112. Min Range: -0.3112

Max Act: 0.2513. Min Act: -0.0000

Data Index: 792268 (C4 (Web Text))

Max Activating Token Index: 851

Text #9

Max Range: 0.3112. Min Range: -0.3112

Max Act: 0.2201. Min Act: -0.0000

Data Index: 1272495 (C4 (Web Text))

Max Activating Token Index: 695

Text #10

Max Range: 0.3112. Min Range: -0.3112

Max Act: 0.2388. Min Act: -0.0000

Data Index: 522075 (C4 (Web Text))

Max Activating Token Index: 740

Text #11

Max Range: 0.3112. Min Range: -0.3112

Max Act: 0.2458. Min Act: -0.0000

Data Index: 1091775 (C4 (Web Text))

Max Activating Token Index: 924

Text #12

Max Range: 0.3112. Min Range: -0.3112

Max Act: 0.2462. Min Act: -0.0000

Data Index: 1251424 (C4 (Web Text))

Max Activating Token Index: 224

Text #13

Max Range: 0.3112. Min Range: -0.3112

Max Act: 0.2247. Min Act: -0.0000

Data Index: 487244 (C4 (Web Text))

Max Activating Token Index: 520

Text #14

Max Range: 0.3112. Min Range: -0.3112

Max Act: 0.2202. Min Act: -0.0000

Data Index: 419263 (C4 (Web Text))

Max Activating Token Index: 938

Text #15

Max Range: 0.3112. Min Range: -0.3112

Max Act: 0.2335. Min Act: -0.0000

Data Index: 384452 (C4 (Web Text))

Max Activating Token Index: 461

Text #16

Max Range: 0.3112. Min Range: -0.3112

Max Act: 0.2109. Min Act: -0.0000

Data Index: 24025 (C4 (Web Text))

Max Activating Token Index: 170

Text #17

Max Range: 0.3112. Min Range: -0.3112

Max Act: 0.2196. Min Act: -0.0000

Data Index: 1030023 (C4 (Web Text))

Max Activating Token Index: 1006

Text #18

Max Range: 0.3112. Min Range: -0.3112

Max Act: 0.2284. Min Act: -0.0000

Data Index: 919791 (C4 (Web Text))

Max Activating Token Index: 719

Text #19

Max Range: 0.3112. Min Range: -0.3112

Max Act: 0.2165. Min Act: -0.0000

Data Index: 78410 (C4 (Web Text))

Max Activating Token Index: 99