Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 281 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2925. Min Range: -0.2925

Max Act: 0.2925. Min Act: -0.0001

Data Index: 557510 (C4 (Web Text))

Max Activating Token Index: 33

Text #1

Max Range: 0.2925. Min Range: -0.2925

Max Act: 0.2699. Min Act: -0.0001

Data Index: 1488286 (Python Code)

Max Activating Token Index: 698

Text #2

Max Range: 0.2925. Min Range: -0.2925

Max Act: 0.2650. Min Act: -0.0001

Data Index: 1601091 (Python Code)

Max Activating Token Index: 698

Text #3

Max Range: 0.2925. Min Range: -0.2925

Max Act: 0.2743. Min Act: -0.0001

Data Index: 302880 (C4 (Web Text))

Max Activating Token Index: 549

Text #4

Max Range: 0.2925. Min Range: -0.2925

Max Act: 0.2651. Min Act: -0.0001

Data Index: 298100 (C4 (Web Text))

Max Activating Token Index: 78

Text #5

Max Range: 0.2925. Min Range: -0.2925

Max Act: 0.2620. Min Act: -0.0001

Data Index: 1554190 (Python Code)

Max Activating Token Index: 469

Text #6

Max Range: 0.2925. Min Range: -0.2925

Max Act: 0.2623. Min Act: -0.0001

Data Index: 631372 (C4 (Web Text))

Max Activating Token Index: 395

Text #7

Max Range: 0.2925. Min Range: -0.2925

Max Act: 0.2640. Min Act: -0.0001

Data Index: 1364417 (Python Code)

Max Activating Token Index: 814

Text #8

Max Range: 0.2925. Min Range: -0.2925

Max Act: 0.2516. Min Act: -0.0001

Data Index: 1473811 (Python Code)

Max Activating Token Index: 87

Text #9

Max Range: 0.2925. Min Range: -0.2925

Max Act: 0.2446. Min Act: -0.0001

Data Index: 1630506 (Python Code)

Max Activating Token Index: 732

Text #10

Max Range: 0.2925. Min Range: -0.2925

Max Act: 0.2454. Min Act: -0.0001

Data Index: 1630298 (Python Code)

Max Activating Token Index: 117

Text #11

Max Range: 0.2925. Min Range: -0.2925

Max Act: 0.2515. Min Act: -0.0001

Data Index: 291389 (C4 (Web Text))

Max Activating Token Index: 674

Text #12

Max Range: 0.2925. Min Range: -0.2925

Max Act: 0.2420. Min Act: -0.0001

Data Index: 1275853 (C4 (Web Text))

Max Activating Token Index: 682

Text #13

Max Range: 0.2925. Min Range: -0.2925

Max Act: 0.2574. Min Act: -0.0001

Data Index: 1540962 (Python Code)

Max Activating Token Index: 713

Text #14

Max Range: 0.2925. Min Range: -0.2925

Max Act: 0.2404. Min Act: -0.0001

Data Index: 1650600 (Python Code)

Max Activating Token Index: 504

Text #15

Max Range: 0.2925. Min Range: -0.2925

Max Act: 0.2486. Min Act: -0.0001

Data Index: 902481 (C4 (Web Text))

Max Activating Token Index: 166

Text #16

Max Range: 0.2925. Min Range: -0.2925

Max Act: 0.2460. Min Act: -0.0001

Data Index: 1454429 (Python Code)

Max Activating Token Index: 694

Text #17

Max Range: 0.2925. Min Range: -0.2925

Max Act: 0.2491. Min Act: -0.0001

Data Index: 1647688 (Python Code)

Max Activating Token Index: 50

Text #18

Max Range: 0.2925. Min Range: -0.2925

Max Act: 0.2535. Min Act: -0.0001

Data Index: 1387692 (Python Code)

Max Activating Token Index: 687

Text #19

Max Range: 0.2925. Min Range: -0.2925

Max Act: 0.2477. Min Act: -0.0001

Data Index: 1646366 (Python Code)

Max Activating Token Index: 58