Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1431 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.4223. Min Range: -1.4223

Max Act: 1.4223. Min Act: -0.0000

Data Index: 178010 (C4 (Web Text))

Max Activating Token Index: 1003

Text #1

Max Range: 1.4223. Min Range: -1.4223

Max Act: 1.2107. Min Act: -0.0000

Data Index: 176670 (C4 (Web Text))

Max Activating Token Index: 640

Text #2

Max Range: 1.4223. Min Range: -1.4223

Max Act: 1.1272. Min Act: -0.0000

Data Index: 1587590 (Python Code)

Max Activating Token Index: 234

Text #3

Max Range: 1.4223. Min Range: -1.4223

Max Act: 1.1176. Min Act: -0.0000

Data Index: 23788 (C4 (Web Text))

Max Activating Token Index: 792

Text #4

Max Range: 1.4223. Min Range: -1.4223

Max Act: 0.9967. Min Act: -0.0000

Data Index: 557890 (C4 (Web Text))

Max Activating Token Index: 298

Text #5

Max Range: 1.4223. Min Range: -1.4223

Max Act: 0.9900. Min Act: -0.0000

Data Index: 1535162 (Python Code)

Max Activating Token Index: 716

Text #6

Max Range: 1.4223. Min Range: -1.4223

Max Act: 1.0052. Min Act: 0.0001

Data Index: 1620361 (Python Code)

Max Activating Token Index: 242

Text #7

Max Range: 1.4223. Min Range: -1.4223

Max Act: 1.0254. Min Act: 0.0001

Data Index: 1624182 (Python Code)

Max Activating Token Index: 359

Text #8

Max Range: 1.4223. Min Range: -1.4223

Max Act: 0.9741. Min Act: -0.0000

Data Index: 1021705 (C4 (Web Text))

Max Activating Token Index: 765

Text #9

Max Range: 1.4223. Min Range: -1.4223

Max Act: 0.8921. Min Act: -0.0000

Data Index: 163310 (C4 (Web Text))

Max Activating Token Index: 309

Text #10

Max Range: 1.4223. Min Range: -1.4223

Max Act: 0.9121. Min Act: -0.0000

Data Index: 1482427 (Python Code)

Max Activating Token Index: 277

Text #11

Max Range: 1.4223. Min Range: -1.4223

Max Act: 0.9336. Min Act: 0.0000

Data Index: 1597491 (Python Code)

Max Activating Token Index: 159

Text #12

Max Range: 1.4223. Min Range: -1.4223

Max Act: 0.7931. Min Act: -0.0000

Data Index: 1490152 (Python Code)

Max Activating Token Index: 749

Text #13

Max Range: 1.4223. Min Range: -1.4223

Max Act: 0.8173. Min Act: -0.0000

Data Index: 84696 (C4 (Web Text))

Max Activating Token Index: 346

Text #14

Max Range: 1.4223. Min Range: -1.4223

Max Act: 0.8580. Min Act: -0.0000

Data Index: 1396742 (Python Code)

Max Activating Token Index: 717

Text #15

Max Range: 1.4223. Min Range: -1.4223

Max Act: 0.7947. Min Act: -0.0000

Data Index: 843496 (C4 (Web Text))

Max Activating Token Index: 463

Text #16

Max Range: 1.4223. Min Range: -1.4223

Max Act: 0.8213. Min Act: 0.0001

Data Index: 1546091 (Python Code)

Max Activating Token Index: 810

Text #17

Max Range: 1.4223. Min Range: -1.4223

Max Act: 0.7718. Min Act: -0.0000

Data Index: 1615454 (Python Code)

Max Activating Token Index: 42

Text #18

Max Range: 1.4223. Min Range: -1.4223

Max Act: 0.7433. Min Act: -0.0000

Data Index: 843244 (C4 (Web Text))

Max Activating Token Index: 552

Text #19

Max Range: 1.4223. Min Range: -1.4223

Max Act: 0.7641. Min Act: 0.0000

Data Index: 1382866 (Python Code)

Max Activating Token Index: 564