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

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

Neuron 2216 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: 0.1648. Min Range: -0.1648

Max Act: 0.1648. Min Act: -0.0000

Data Index: 525767 (C4 (Web Text))

Max Activating Token Index: 501

Text #1

Max Range: 0.1648. Min Range: -0.1648

Max Act: 0.1605. Min Act: -0.0000

Data Index: 392523 (C4 (Web Text))

Max Activating Token Index: 449

Text #2

Max Range: 0.1648. Min Range: -0.1648

Max Act: 0.1469. Min Act: -0.0000

Data Index: 177786 (C4 (Web Text))

Max Activating Token Index: 130

Text #3

Max Range: 0.1648. Min Range: -0.1648

Max Act: 0.1403. Min Act: -0.0000

Data Index: 1195582 (C4 (Web Text))

Max Activating Token Index: 771

Text #4

Max Range: 0.1648. Min Range: -0.1648

Max Act: 0.1350. Min Act: -0.0000

Data Index: 242206 (C4 (Web Text))

Max Activating Token Index: 197

Text #5

Max Range: 0.1648. Min Range: -0.1648

Max Act: 0.1309. Min Act: -0.0000

Data Index: 1242620 (C4 (Web Text))

Max Activating Token Index: 11

Text #6

Max Range: 0.1648. Min Range: -0.1648

Max Act: 0.1275. Min Act: -0.0000

Data Index: 286796 (C4 (Web Text))

Max Activating Token Index: 90

Text #7

Max Range: 0.1648. Min Range: -0.1648

Max Act: 0.1179. Min Act: -0.0000

Data Index: 1224064 (C4 (Web Text))

Max Activating Token Index: 825

Text #8

Max Range: 0.1648. Min Range: -0.1648

Max Act: 0.1182. Min Act: -0.0000

Data Index: 1301996 (C4 (Web Text))

Max Activating Token Index: 223

Text #9

Max Range: 0.1648. Min Range: -0.1648

Max Act: 0.1177. Min Act: -0.0000

Data Index: 1178087 (C4 (Web Text))

Max Activating Token Index: 917

Text #10

Max Range: 0.1648. Min Range: -0.1648

Max Act: 0.1134. Min Act: -0.0000

Data Index: 514323 (C4 (Web Text))

Max Activating Token Index: 238

Text #11

Max Range: 0.1648. Min Range: -0.1648

Max Act: 0.1166. Min Act: -0.0000

Data Index: 4204 (C4 (Web Text))

Max Activating Token Index: 104

Text #12

Max Range: 0.1648. Min Range: -0.1648

Max Act: 0.1115. Min Act: -0.0000

Data Index: 683689 (C4 (Web Text))

Max Activating Token Index: 1006

Text #13

Max Range: 0.1648. Min Range: -0.1648

Max Act: 0.1152. Min Act: -0.0000

Data Index: 140018 (C4 (Web Text))

Max Activating Token Index: 615

Text #14

Max Range: 0.1648. Min Range: -0.1648

Max Act: 0.1102. Min Act: -0.0000

Data Index: 386413 (C4 (Web Text))

Max Activating Token Index: 700

Text #15

Max Range: 0.1648. Min Range: -0.1648

Max Act: 0.1062. Min Act: -0.0000

Data Index: 409883 (C4 (Web Text))

Max Activating Token Index: 689

Text #16

Max Range: 0.1648. Min Range: -0.1648

Max Act: 0.1064. Min Act: -0.0000

Data Index: 98549 (C4 (Web Text))

Max Activating Token Index: 890

Text #17

Max Range: 0.1648. Min Range: -0.1648

Max Act: 0.1062. Min Act: -0.0000

Data Index: 522422 (C4 (Web Text))

Max Activating Token Index: 648

Text #18

Max Range: 0.1648. Min Range: -0.1648

Max Act: 0.1080. Min Act: -0.0000

Data Index: 974783 (C4 (Web Text))

Max Activating Token Index: 312

Text #19

Max Range: 0.1648. Min Range: -0.1648

Max Act: 0.1038. Min Act: -0.0000

Data Index: 990887 (C4 (Web Text))

Max Activating Token Index: 357