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

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

Neuron 1132 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: 0.0350. Min Range: -0.0350

Max Act: 0.0350. Min Act: -0.0006

Data Index: 509239 (C4 (Web Text))

Max Activating Token Index: 191

Text #1

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0344. Min Act: -0.0006

Data Index: 142165 (C4 (Web Text))

Max Activating Token Index: 375

Text #2

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0329. Min Act: -0.0006

Data Index: 902527 (C4 (Web Text))

Max Activating Token Index: 478

Text #3

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0301. Min Act: -0.0006

Data Index: 615555 (C4 (Web Text))

Max Activating Token Index: 662

Text #4

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0303. Min Act: -0.0006

Data Index: 1014183 (C4 (Web Text))

Max Activating Token Index: 143

Text #5

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0300. Min Act: -0.0006

Data Index: 1477647 (Python Code)

Max Activating Token Index: 500

Text #6

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0287. Min Act: -0.0006

Data Index: 662884 (C4 (Web Text))

Max Activating Token Index: 675

Text #7

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0288. Min Act: -0.0006

Data Index: 85889 (C4 (Web Text))

Max Activating Token Index: 108

Text #8

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0284. Min Act: -0.0006

Data Index: 15335 (C4 (Web Text))

Max Activating Token Index: 653

Text #9

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0283. Min Act: -0.0006

Data Index: 69644 (C4 (Web Text))

Max Activating Token Index: 753

Text #10

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0282. Min Act: -0.0006

Data Index: 217315 (C4 (Web Text))

Max Activating Token Index: 616

Text #11

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0282. Min Act: -0.0006

Data Index: 1443319 (Python Code)

Max Activating Token Index: 432

Text #12

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0278. Min Act: -0.0006

Data Index: 1640123 (Python Code)

Max Activating Token Index: 401

Text #13

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0272. Min Act: -0.0006

Data Index: 195794 (C4 (Web Text))

Max Activating Token Index: 648

Text #14

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0266. Min Act: -0.0006

Data Index: 1384388 (Python Code)

Max Activating Token Index: 633

Text #15

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0267. Min Act: -0.0006

Data Index: 1234776 (C4 (Web Text))

Max Activating Token Index: 393

Text #16

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0267. Min Act: -0.0006

Data Index: 1369993 (Python Code)

Max Activating Token Index: 423

Text #17

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0266. Min Act: -0.0006

Data Index: 219103 (C4 (Web Text))

Max Activating Token Index: 395

Text #18

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0266. Min Act: -0.0006

Data Index: 1504053 (Python Code)

Max Activating Token Index: 472

Text #19

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0256. Min Act: -0.0006

Data Index: 305501 (C4 (Web Text))

Max Activating Token Index: 798