Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2494 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3570. Min Range: -0.3570

Max Act: 0.3570. Min Act: -0.0000

Data Index: 621550 (C4 (Web Text))

Max Activating Token Index: 523

Text #1

Max Range: 0.3570. Min Range: -0.3570

Max Act: 0.3008. Min Act: -0.0000

Data Index: 476839 (C4 (Web Text))

Max Activating Token Index: 303

Text #2

Max Range: 0.3570. Min Range: -0.3570

Max Act: 0.2763. Min Act: -0.0000

Data Index: 47784 (C4 (Web Text))

Max Activating Token Index: 836

Text #3

Max Range: 0.3570. Min Range: -0.3570

Max Act: 0.2748. Min Act: -0.0000

Data Index: 1553239 (Python Code)

Max Activating Token Index: 936

Text #4

Max Range: 0.3570. Min Range: -0.3570

Max Act: 0.2826. Min Act: -0.0000

Data Index: 1074424 (C4 (Web Text))

Max Activating Token Index: 397

Text #5

Max Range: 0.3570. Min Range: -0.3570

Max Act: 0.2700. Min Act: -0.0000

Data Index: 770622 (C4 (Web Text))

Max Activating Token Index: 653

Text #6

Max Range: 0.3570. Min Range: -0.3570

Max Act: 0.2893. Min Act: -0.0000

Data Index: 1562942 (Python Code)

Max Activating Token Index: 490

Text #7

Max Range: 0.3570. Min Range: -0.3570

Max Act: 0.2694. Min Act: -0.0000

Data Index: 222864 (C4 (Web Text))

Max Activating Token Index: 525

Text #8

Max Range: 0.3570. Min Range: -0.3570

Max Act: 0.2499. Min Act: -0.0000

Data Index: 1419675 (Python Code)

Max Activating Token Index: 249

Text #9

Max Range: 0.3570. Min Range: -0.3570

Max Act: 0.2607. Min Act: -0.0000

Data Index: 1003401 (C4 (Web Text))

Max Activating Token Index: 782

Text #10

Max Range: 0.3570. Min Range: -0.3570

Max Act: 0.2639. Min Act: -0.0000

Data Index: 1314368 (C4 (Web Text))

Max Activating Token Index: 250

Text #11

Max Range: 0.3570. Min Range: -0.3570

Max Act: 0.2455. Min Act: -0.0000

Data Index: 1232620 (C4 (Web Text))

Max Activating Token Index: 206

Text #12

Max Range: 0.3570. Min Range: -0.3570

Max Act: 0.2631. Min Act: -0.0000

Data Index: 536527 (C4 (Web Text))

Max Activating Token Index: 252

Text #13

Max Range: 0.3570. Min Range: -0.3570

Max Act: 0.2522. Min Act: -0.0000

Data Index: 1279814 (C4 (Web Text))

Max Activating Token Index: 528

Text #14

Max Range: 0.3570. Min Range: -0.3570

Max Act: 0.2519. Min Act: -0.0000

Data Index: 445413 (C4 (Web Text))

Max Activating Token Index: 230

Text #15

Max Range: 0.3570. Min Range: -0.3570

Max Act: 0.2433. Min Act: -0.0000

Data Index: 38510 (C4 (Web Text))

Max Activating Token Index: 429

Text #16

Max Range: 0.3570. Min Range: -0.3570

Max Act: 0.2491. Min Act: -0.0000

Data Index: 1620789 (Python Code)

Max Activating Token Index: 227

Text #17

Max Range: 0.3570. Min Range: -0.3570

Max Act: 0.2517. Min Act: -0.0000

Data Index: 442866 (C4 (Web Text))

Max Activating Token Index: 237

Text #18

Max Range: 0.3570. Min Range: -0.3570

Max Act: 0.2326. Min Act: -0.0000

Data Index: 1086214 (C4 (Web Text))

Max Activating Token Index: 276

Text #19

Max Range: 0.3570. Min Range: -0.3570

Max Act: 0.2506. Min Act: -0.0000

Data Index: 889749 (C4 (Web Text))

Max Activating Token Index: 694