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

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

Neuron 1711 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9577. Min Range: -3.9577

Max Act: 3.9577. Min Act: -0.0000

Data Index: 160998 (C4 (Web Text))

Max Activating Token Index: 270

Text #1

Max Range: 3.9577. Min Range: -3.9577

Max Act: 3.5010. Min Act: -0.0000

Data Index: 775380 (C4 (Web Text))

Max Activating Token Index: 1021

Text #2

Max Range: 3.9577. Min Range: -3.9577

Max Act: 3.4624. Min Act: -0.0000

Data Index: 790315 (C4 (Web Text))

Max Activating Token Index: 676

Text #3

Max Range: 3.9577. Min Range: -3.9577

Max Act: 3.5482. Min Act: -0.0000

Data Index: 160545 (C4 (Web Text))

Max Activating Token Index: 354

Text #4

Max Range: 3.9577. Min Range: -3.9577

Max Act: 3.4912. Min Act: -0.0000

Data Index: 179647 (C4 (Web Text))

Max Activating Token Index: 505

Text #5

Max Range: 3.9577. Min Range: -3.9577

Max Act: 3.2387. Min Act: -0.0000

Data Index: 1396571 (Python Code)

Max Activating Token Index: 211

Text #6

Max Range: 3.9577. Min Range: -3.9577

Max Act: 3.1233. Min Act: -0.0000

Data Index: 514756 (C4 (Web Text))

Max Activating Token Index: 204

Text #7

Max Range: 3.9577. Min Range: -3.9577

Max Act: 3.0997. Min Act: -0.0000

Data Index: 1185632 (C4 (Web Text))

Max Activating Token Index: 371

Text #8

Max Range: 3.9577. Min Range: -3.9577

Max Act: 3.0483. Min Act: -0.0000

Data Index: 474459 (C4 (Web Text))

Max Activating Token Index: 27

Text #9

Max Range: 3.9577. Min Range: -3.9577

Max Act: 2.9950. Min Act: -0.0000

Data Index: 717206 (C4 (Web Text))

Max Activating Token Index: 994

Text #10

Max Range: 3.9577. Min Range: -3.9577

Max Act: 3.1110. Min Act: -0.0000

Data Index: 1565720 (Python Code)

Max Activating Token Index: 378

Text #11

Max Range: 3.9577. Min Range: -3.9577

Max Act: 2.9755. Min Act: -0.0000

Data Index: 289473 (C4 (Web Text))

Max Activating Token Index: 687

Text #12

Max Range: 3.9577. Min Range: -3.9577

Max Act: 2.9427. Min Act: -0.0000

Data Index: 680117 (C4 (Web Text))

Max Activating Token Index: 185

Text #13

Max Range: 3.9577. Min Range: -3.9577

Max Act: 2.9139. Min Act: -0.0000

Data Index: 806655 (C4 (Web Text))

Max Activating Token Index: 751

Text #14

Max Range: 3.9577. Min Range: -3.9577

Max Act: 2.8925. Min Act: -0.0000

Data Index: 1200628 (C4 (Web Text))

Max Activating Token Index: 166

Text #15

Max Range: 3.9577. Min Range: -3.9577

Max Act: 2.8248. Min Act: -0.0000

Data Index: 1478869 (Python Code)

Max Activating Token Index: 704

Text #16

Max Range: 3.9577. Min Range: -3.9577

Max Act: 2.8244. Min Act: -0.0000

Data Index: 309865 (C4 (Web Text))

Max Activating Token Index: 791

Text #17

Max Range: 3.9577. Min Range: -3.9577

Max Act: 2.8098. Min Act: -0.0000

Data Index: 82188 (C4 (Web Text))

Max Activating Token Index: 299

Text #18

Max Range: 3.9577. Min Range: -3.9577

Max Act: 2.8206. Min Act: -0.0000

Data Index: 319090 (C4 (Web Text))

Max Activating Token Index: 519

Text #19

Max Range: 3.9577. Min Range: -3.9577

Max Act: 2.7223. Min Act: -0.0000

Data Index: 1374385 (Python Code)

Max Activating Token Index: 257