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

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

Neuron 5590 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: 0.3850. Min Range: -0.3850

Max Act: 0.3528. Min Act: -0.0000

Data Index: 1396025 (Python Code)

Max Activating Token Index: 859

Text #1

Max Range: 0.3850. Min Range: -0.3850

Max Act: 0.3850. Min Act: -0.0000

Data Index: 1360274 (Python Code)

Max Activating Token Index: 536

Text #2

Max Range: 0.3850. Min Range: -0.3850

Max Act: 0.3339. Min Act: -0.0000

Data Index: 935801 (C4 (Web Text))

Max Activating Token Index: 924

Text #3

Max Range: 0.3850. Min Range: -0.3850

Max Act: 0.3395. Min Act: -0.0000

Data Index: 48869 (C4 (Web Text))

Max Activating Token Index: 447

Text #4

Max Range: 0.3850. Min Range: -0.3850

Max Act: 0.3212. Min Act: -0.0000

Data Index: 1535140 (Python Code)

Max Activating Token Index: 640

Text #5

Max Range: 0.3850. Min Range: -0.3850

Max Act: 0.3079. Min Act: -0.0000

Data Index: 660699 (C4 (Web Text))

Max Activating Token Index: 941

Text #6

Max Range: 0.3850. Min Range: -0.3850

Max Act: 0.2862. Min Act: -0.0000

Data Index: 341005 (C4 (Web Text))

Max Activating Token Index: 21

Text #7

Max Range: 0.3850. Min Range: -0.3850

Max Act: 0.2715. Min Act: -0.0000

Data Index: 1609761 (Python Code)

Max Activating Token Index: 667

Text #8

Max Range: 0.3850. Min Range: -0.3850

Max Act: 0.2859. Min Act: -0.0000

Data Index: 1451646 (Python Code)

Max Activating Token Index: 328

Text #9

Max Range: 0.3850. Min Range: -0.3850

Max Act: 0.2679. Min Act: -0.0000

Data Index: 776088 (C4 (Web Text))

Max Activating Token Index: 720

Text #10

Max Range: 0.3850. Min Range: -0.3850

Max Act: 0.2559. Min Act: -0.0000

Data Index: 45534 (C4 (Web Text))

Max Activating Token Index: 922

Text #11

Max Range: 0.3850. Min Range: -0.3850

Max Act: 0.2691. Min Act: -0.0000

Data Index: 190361 (C4 (Web Text))

Max Activating Token Index: 146

Text #12

Max Range: 0.3850. Min Range: -0.3850

Max Act: 0.2540. Min Act: -0.0000

Data Index: 1547601 (Python Code)

Max Activating Token Index: 210

Text #13

Max Range: 0.3850. Min Range: -0.3850

Max Act: 0.2538. Min Act: -0.0000

Data Index: 841964 (C4 (Web Text))

Max Activating Token Index: 749

Text #14

Max Range: 0.3850. Min Range: -0.3850

Max Act: 0.2449. Min Act: -0.0000

Data Index: 1026058 (C4 (Web Text))

Max Activating Token Index: 126

Text #15

Max Range: 0.3850. Min Range: -0.3850

Max Act: 0.2638. Min Act: -0.0000

Data Index: 705357 (C4 (Web Text))

Max Activating Token Index: 450

Text #16

Max Range: 0.3850. Min Range: -0.3850

Max Act: 0.2563. Min Act: -0.0000

Data Index: 1383891 (Python Code)

Max Activating Token Index: 852

Text #17

Max Range: 0.3850. Min Range: -0.3850

Max Act: 0.2549. Min Act: -0.0000

Data Index: 834129 (C4 (Web Text))

Max Activating Token Index: 544

Text #18

Max Range: 0.3850. Min Range: -0.3850

Max Act: 0.2515. Min Act: -0.0000

Data Index: 836834 (C4 (Web Text))

Max Activating Token Index: 574

Text #19

Max Range: 0.3850. Min Range: -0.3850

Max Act: 0.2403. Min Act: -0.0000

Data Index: 1655517 (Python Code)

Max Activating Token Index: 244