Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 740 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0291. Min Range: -0.0291

Max Act: 0.0291. Min Act: -0.0006

Data Index: 24996 (C4 (Web Text))

Max Activating Token Index: 515

Text #1

Max Range: 0.0291. Min Range: -0.0291

Max Act: 0.0279. Min Act: -0.0006

Data Index: 273358 (C4 (Web Text))

Max Activating Token Index: 807

Text #2

Max Range: 0.0291. Min Range: -0.0291

Max Act: 0.0269. Min Act: -0.0005

Data Index: 429923 (C4 (Web Text))

Max Activating Token Index: 599

Text #3

Max Range: 0.0291. Min Range: -0.0291

Max Act: 0.0259. Min Act: -0.0006

Data Index: 1332767 (C4 (Web Text))

Max Activating Token Index: 299

Text #4

Max Range: 0.0291. Min Range: -0.0291

Max Act: 0.0250. Min Act: -0.0006

Data Index: 1163943 (C4 (Web Text))

Max Activating Token Index: 267

Text #5

Max Range: 0.0291. Min Range: -0.0291

Max Act: 0.0262. Min Act: -0.0006

Data Index: 109727 (C4 (Web Text))

Max Activating Token Index: 522

Text #6

Max Range: 0.0291. Min Range: -0.0291

Max Act: 0.0249. Min Act: -0.0006

Data Index: 392703 (C4 (Web Text))

Max Activating Token Index: 682

Text #7

Max Range: 0.0291. Min Range: -0.0291

Max Act: 0.0255. Min Act: -0.0006

Data Index: 848010 (C4 (Web Text))

Max Activating Token Index: 654

Text #8

Max Range: 0.0291. Min Range: -0.0291

Max Act: 0.0254. Min Act: -0.0006

Data Index: 602008 (C4 (Web Text))

Max Activating Token Index: 348

Text #9

Max Range: 0.0291. Min Range: -0.0291

Max Act: 0.0253. Min Act: -0.0006

Data Index: 910422 (C4 (Web Text))

Max Activating Token Index: 827

Text #10

Max Range: 0.0291. Min Range: -0.0291

Max Act: 0.0248. Min Act: -0.0006

Data Index: 1455638 (Python Code)

Max Activating Token Index: 269

Text #11

Max Range: 0.0291. Min Range: -0.0291

Max Act: 0.0251. Min Act: -0.0006

Data Index: 600160 (C4 (Web Text))

Max Activating Token Index: 309

Text #12

Max Range: 0.0291. Min Range: -0.0291

Max Act: 0.0238. Min Act: -0.0006

Data Index: 1598774 (Python Code)

Max Activating Token Index: 474

Text #13

Max Range: 0.0291. Min Range: -0.0291

Max Act: 0.0234. Min Act: -0.0006

Data Index: 1378536 (Python Code)

Max Activating Token Index: 102

Text #14

Max Range: 0.0291. Min Range: -0.0291

Max Act: 0.0238. Min Act: -0.0006

Data Index: 1289480 (C4 (Web Text))

Max Activating Token Index: 61

Text #15

Max Range: 0.0291. Min Range: -0.0291

Max Act: 0.0248. Min Act: -0.0006

Data Index: 392510 (C4 (Web Text))

Max Activating Token Index: 256

Text #16

Max Range: 0.0291. Min Range: -0.0291

Max Act: 0.0237. Min Act: -0.0006

Data Index: 1474271 (Python Code)

Max Activating Token Index: 342

Text #17

Max Range: 0.0291. Min Range: -0.0291

Max Act: 0.0236. Min Act: -0.0006

Data Index: 1216354 (C4 (Web Text))

Max Activating Token Index: 610

Text #18

Max Range: 0.0291. Min Range: -0.0291

Max Act: 0.0231. Min Act: -0.0006

Data Index: 992714 (C4 (Web Text))

Max Activating Token Index: 507

Text #19

Max Range: 0.0291. Min Range: -0.0291

Max Act: 0.0230. Min Act: -0.0006

Data Index: 1513120 (Python Code)

Max Activating Token Index: 257