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

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

Neuron 4622 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: 5.4994. Min Range: -5.4994

Max Act: 5.4994. Min Act: -0.0000

Data Index: 1535877 (Python Code)

Max Activating Token Index: 838

Text #1

Max Range: 5.4994. Min Range: -5.4994

Max Act: 4.9885. Min Act: -0.0000

Data Index: 652655 (C4 (Web Text))

Max Activating Token Index: 487

Text #2

Max Range: 5.4994. Min Range: -5.4994

Max Act: 4.9655. Min Act: -0.0000

Data Index: 1628595 (Python Code)

Max Activating Token Index: 208

Text #3

Max Range: 5.4994. Min Range: -5.4994

Max Act: 4.6139. Min Act: -0.0000

Data Index: 1556169 (Python Code)

Max Activating Token Index: 410

Text #4

Max Range: 5.4994. Min Range: -5.4994

Max Act: 4.6345. Min Act: -0.0000

Data Index: 1530276 (Python Code)

Max Activating Token Index: 270

Text #5

Max Range: 5.4994. Min Range: -5.4994

Max Act: 4.6566. Min Act: -0.0000

Data Index: 1483537 (Python Code)

Max Activating Token Index: 998

Text #6

Max Range: 5.4994. Min Range: -5.4994

Max Act: 4.1999. Min Act: -0.0000

Data Index: 953905 (C4 (Web Text))

Max Activating Token Index: 326

Text #7

Max Range: 5.4994. Min Range: -5.4994

Max Act: 4.8379. Min Act: -0.0000

Data Index: 1140672 (C4 (Web Text))

Max Activating Token Index: 738

Text #8

Max Range: 5.4994. Min Range: -5.4994

Max Act: 4.9247. Min Act: -0.0000

Data Index: 1624209 (Python Code)

Max Activating Token Index: 355

Text #9

Max Range: 5.4994. Min Range: -5.4994

Max Act: 4.2363. Min Act: -0.0000

Data Index: 1134643 (C4 (Web Text))

Max Activating Token Index: 317

Text #10

Max Range: 5.4994. Min Range: -5.4994

Max Act: 3.7289. Min Act: -0.0000

Data Index: 569201 (C4 (Web Text))

Max Activating Token Index: 294

Text #11

Max Range: 5.4994. Min Range: -5.4994

Max Act: 3.8546. Min Act: -0.0000

Data Index: 893403 (C4 (Web Text))

Max Activating Token Index: 916

Text #12

Max Range: 5.4994. Min Range: -5.4994

Max Act: 4.1696. Min Act: -0.0000

Data Index: 571457 (C4 (Web Text))

Max Activating Token Index: 914

Text #13

Max Range: 5.4994. Min Range: -5.4994

Max Act: 4.0911. Min Act: -0.0000

Data Index: 1474476 (Python Code)

Max Activating Token Index: 285

Text #14

Max Range: 5.4994. Min Range: -5.4994

Max Act: 3.8989. Min Act: -0.0000

Data Index: 377523 (C4 (Web Text))

Max Activating Token Index: 409

Text #15

Max Range: 5.4994. Min Range: -5.4994

Max Act: 3.8267. Min Act: -0.0000

Data Index: 1390216 (Python Code)

Max Activating Token Index: 526

Text #16

Max Range: 5.4994. Min Range: -5.4994

Max Act: 3.6033. Min Act: -0.0000

Data Index: 1598598 (Python Code)

Max Activating Token Index: 435

Text #17

Max Range: 5.4994. Min Range: -5.4994

Max Act: 3.7457. Min Act: -0.0000

Data Index: 1106330 (C4 (Web Text))

Max Activating Token Index: 996

Text #18

Max Range: 5.4994. Min Range: -5.4994

Max Act: 3.6858. Min Act: -0.0000

Data Index: 1565631 (Python Code)

Max Activating Token Index: 208

Text #19

Max Range: 5.4994. Min Range: -5.4994

Max Act: 3.6387. Min Act: -0.0000

Data Index: 920087 (C4 (Web Text))

Max Activating Token Index: 859