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

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

Neuron 2593 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1681. Min Range: -2.1681

Max Act: 2.1681. Min Act: -0.0000

Data Index: 4466 (C4 (Web Text))

Max Activating Token Index: 806

Text #1

Max Range: 2.1681. Min Range: -2.1681

Max Act: 1.9304. Min Act: -0.0000

Data Index: 194168 (C4 (Web Text))

Max Activating Token Index: 385

Text #2

Max Range: 2.1681. Min Range: -2.1681

Max Act: 1.7727. Min Act: -0.0000

Data Index: 987378 (C4 (Web Text))

Max Activating Token Index: 577

Text #3

Max Range: 2.1681. Min Range: -2.1681

Max Act: 1.5501. Min Act: -0.0000

Data Index: 1343094 (C4 (Web Text))

Max Activating Token Index: 906

Text #4

Max Range: 2.1681. Min Range: -2.1681

Max Act: 1.5844. Min Act: -0.0000

Data Index: 610438 (C4 (Web Text))

Max Activating Token Index: 89

Text #5

Max Range: 2.1681. Min Range: -2.1681

Max Act: 1.5760. Min Act: -0.0000

Data Index: 239361 (C4 (Web Text))

Max Activating Token Index: 36

Text #6

Max Range: 2.1681. Min Range: -2.1681

Max Act: 1.5641. Min Act: -0.0000

Data Index: 1280378 (C4 (Web Text))

Max Activating Token Index: 558

Text #7

Max Range: 2.1681. Min Range: -2.1681

Max Act: 1.5319. Min Act: -0.0000

Data Index: 587892 (C4 (Web Text))

Max Activating Token Index: 67

Text #8

Max Range: 2.1681. Min Range: -2.1681

Max Act: 1.4305. Min Act: -0.0000

Data Index: 856629 (C4 (Web Text))

Max Activating Token Index: 87

Text #9

Max Range: 2.1681. Min Range: -2.1681

Max Act: 1.5982. Min Act: -0.0000

Data Index: 1288621 (C4 (Web Text))

Max Activating Token Index: 433

Text #10

Max Range: 2.1681. Min Range: -2.1681

Max Act: 1.4660. Min Act: -0.0000

Data Index: 498135 (C4 (Web Text))

Max Activating Token Index: 224

Text #11

Max Range: 2.1681. Min Range: -2.1681

Max Act: 1.3368. Min Act: -0.0000

Data Index: 1346460 (C4 (Web Text))

Max Activating Token Index: 49

Text #12

Max Range: 2.1681. Min Range: -2.1681

Max Act: 1.4875. Min Act: -0.0000

Data Index: 1187218 (C4 (Web Text))

Max Activating Token Index: 301

Text #13

Max Range: 2.1681. Min Range: -2.1681

Max Act: 1.3710. Min Act: -0.0000

Data Index: 729714 (C4 (Web Text))

Max Activating Token Index: 928

Text #14

Max Range: 2.1681. Min Range: -2.1681

Max Act: 1.3450. Min Act: -0.0000

Data Index: 850335 (C4 (Web Text))

Max Activating Token Index: 92

Text #15

Max Range: 2.1681. Min Range: -2.1681

Max Act: 1.2190. Min Act: -0.0000

Data Index: 1100335 (C4 (Web Text))

Max Activating Token Index: 809

Text #16

Max Range: 2.1681. Min Range: -2.1681

Max Act: 1.2994. Min Act: -0.0000

Data Index: 374982 (C4 (Web Text))

Max Activating Token Index: 739

Text #17

Max Range: 2.1681. Min Range: -2.1681

Max Act: 1.2726. Min Act: -0.0000

Data Index: 1160565 (C4 (Web Text))

Max Activating Token Index: 583

Text #18

Max Range: 2.1681. Min Range: -2.1681

Max Act: 1.2539. Min Act: -0.0000

Data Index: 1167576 (C4 (Web Text))

Max Activating Token Index: 620

Text #19

Max Range: 2.1681. Min Range: -2.1681

Max Act: 1.2167. Min Act: -0.0000

Data Index: 400904 (C4 (Web Text))

Max Activating Token Index: 1020