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

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

Neuron 2009 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0368. Min Act: -0.0001

Data Index: 1272313 (C4 (Web Text))

Max Activating Token Index: 1017

Text #1

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0346. Min Act: -0.0001

Data Index: 930580 (C4 (Web Text))

Max Activating Token Index: 158

Text #2

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0335. Min Act: -0.0001

Data Index: 1057072 (C4 (Web Text))

Max Activating Token Index: 858

Text #3

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0299. Min Act: -0.0001

Data Index: 1282989 (C4 (Web Text))

Max Activating Token Index: 211

Text #4

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0297. Min Act: -0.0001

Data Index: 1626775 (Python Code)

Max Activating Token Index: 971

Text #5

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0312. Min Act: -0.0001

Data Index: 1361269 (Python Code)

Max Activating Token Index: 868

Text #6

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0269. Min Act: -0.0001

Data Index: 386387 (C4 (Web Text))

Max Activating Token Index: 597

Text #7

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0300. Min Act: -0.0001

Data Index: 1271077 (C4 (Web Text))

Max Activating Token Index: 305

Text #8

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0276. Min Act: -0.0001

Data Index: 628841 (C4 (Web Text))

Max Activating Token Index: 160

Text #9

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0275. Min Act: -0.0001

Data Index: 532897 (C4 (Web Text))

Max Activating Token Index: 36

Text #10

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0271. Min Act: -0.0001

Data Index: 508622 (C4 (Web Text))

Max Activating Token Index: 552

Text #11

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0260. Min Act: -0.0001

Data Index: 1131616 (C4 (Web Text))

Max Activating Token Index: 238

Text #12

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0261. Min Act: -0.0001

Data Index: 1448064 (Python Code)

Max Activating Token Index: 685

Text #13

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0253. Min Act: -0.0001

Data Index: 795284 (C4 (Web Text))

Max Activating Token Index: 296

Text #14

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0248. Min Act: -0.0001

Data Index: 1508447 (Python Code)

Max Activating Token Index: 540

Text #15

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0242. Min Act: -0.0001

Data Index: 1479060 (Python Code)

Max Activating Token Index: 211

Text #16

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0248. Min Act: -0.0001

Data Index: 728252 (C4 (Web Text))

Max Activating Token Index: 514

Text #17

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0250. Min Act: -0.0001

Data Index: 855347 (C4 (Web Text))

Max Activating Token Index: 54

Text #18

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0250. Min Act: -0.0001

Data Index: 980895 (C4 (Web Text))

Max Activating Token Index: 214

Text #19

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0231. Min Act: -0.0001

Data Index: 392289 (C4 (Web Text))

Max Activating Token Index: 83