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

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

Neuron 1779 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.2248. Min Range: -4.2248

Max Act: 3.9107. Min Act: -0.0000

Data Index: 356012 (C4 (Web Text))

Max Activating Token Index: 500

Text #1

Max Range: 4.2248. Min Range: -4.2248

Max Act: 4.2248. Min Act: -0.0000

Data Index: 799543 (C4 (Web Text))

Max Activating Token Index: 335

Text #2

Max Range: 4.2248. Min Range: -4.2248

Max Act: 3.9934. Min Act: -0.0000

Data Index: 1351509 (C4 (Web Text))

Max Activating Token Index: 484

Text #3

Max Range: 4.2248. Min Range: -4.2248

Max Act: 4.1236. Min Act: -0.0000

Data Index: 431230 (C4 (Web Text))

Max Activating Token Index: 232

Text #4

Max Range: 4.2248. Min Range: -4.2248

Max Act: 3.8936. Min Act: -0.0000

Data Index: 1417375 (Python Code)

Max Activating Token Index: 252

Text #5

Max Range: 4.2248. Min Range: -4.2248

Max Act: 3.8493. Min Act: -0.0000

Data Index: 286983 (C4 (Web Text))

Max Activating Token Index: 381

Text #6

Max Range: 4.2248. Min Range: -4.2248

Max Act: 3.7403. Min Act: -0.0000

Data Index: 183218 (C4 (Web Text))

Max Activating Token Index: 628

Text #7

Max Range: 4.2248. Min Range: -4.2248

Max Act: 3.7201. Min Act: -0.0000

Data Index: 359291 (C4 (Web Text))

Max Activating Token Index: 523

Text #8

Max Range: 4.2248. Min Range: -4.2248

Max Act: 3.7925. Min Act: -0.0000

Data Index: 504871 (C4 (Web Text))

Max Activating Token Index: 244

Text #9

Max Range: 4.2248. Min Range: -4.2248

Max Act: 3.5960. Min Act: -0.0000

Data Index: 956400 (C4 (Web Text))

Max Activating Token Index: 626

Text #10

Max Range: 4.2248. Min Range: -4.2248

Max Act: 3.5798. Min Act: -0.0000

Data Index: 1328926 (C4 (Web Text))

Max Activating Token Index: 544

Text #11

Max Range: 4.2248. Min Range: -4.2248

Max Act: 3.5724. Min Act: -0.0000

Data Index: 612575 (C4 (Web Text))

Max Activating Token Index: 237

Text #12

Max Range: 4.2248. Min Range: -4.2248

Max Act: 3.5668. Min Act: -0.0000

Data Index: 985929 (C4 (Web Text))

Max Activating Token Index: 327

Text #13

Max Range: 4.2248. Min Range: -4.2248

Max Act: 3.5465. Min Act: -0.0000

Data Index: 1337407 (C4 (Web Text))

Max Activating Token Index: 275

Text #14

Max Range: 4.2248. Min Range: -4.2248

Max Act: 3.6752. Min Act: -0.0000

Data Index: 1239307 (C4 (Web Text))

Max Activating Token Index: 395

Text #15

Max Range: 4.2248. Min Range: -4.2248

Max Act: 3.3794. Min Act: -0.0000

Data Index: 146904 (C4 (Web Text))

Max Activating Token Index: 292

Text #16

Max Range: 4.2248. Min Range: -4.2248

Max Act: 3.5053. Min Act: -0.0000

Data Index: 1299503 (C4 (Web Text))

Max Activating Token Index: 648

Text #17

Max Range: 4.2248. Min Range: -4.2248

Max Act: 3.4775. Min Act: -0.0000

Data Index: 725121 (C4 (Web Text))

Max Activating Token Index: 71

Text #18

Max Range: 4.2248. Min Range: -4.2248

Max Act: 3.6235. Min Act: -0.0000

Data Index: 202521 (C4 (Web Text))

Max Activating Token Index: 111

Text #19

Max Range: 4.2248. Min Range: -4.2248

Max Act: 3.6522. Min Act: -0.0000

Data Index: 1518482 (Python Code)

Max Activating Token Index: 913