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

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

Neuron 3892 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5428. Min Range: -1.5428

Max Act: 1.5428. Min Act: -0.0001

Data Index: 116822 (C4 (Web Text))

Max Activating Token Index: 406

Text #1

Max Range: 1.5428. Min Range: -1.5428

Max Act: 1.4825. Min Act: -0.0001

Data Index: 1336588 (C4 (Web Text))

Max Activating Token Index: 547

Text #2

Max Range: 1.5428. Min Range: -1.5428

Max Act: 1.4739. Min Act: -0.0001

Data Index: 265135 (C4 (Web Text))

Max Activating Token Index: 515

Text #3

Max Range: 1.5428. Min Range: -1.5428

Max Act: 1.2491. Min Act: -0.0001

Data Index: 960907 (C4 (Web Text))

Max Activating Token Index: 328

Text #4

Max Range: 1.5428. Min Range: -1.5428

Max Act: 1.1518. Min Act: -0.0000

Data Index: 1167913 (C4 (Web Text))

Max Activating Token Index: 893

Text #5

Max Range: 1.5428. Min Range: -1.5428

Max Act: 1.2875. Min Act: -0.0001

Data Index: 801349 (C4 (Web Text))

Max Activating Token Index: 349

Text #6

Max Range: 1.5428. Min Range: -1.5428

Max Act: 1.2158. Min Act: -0.0001

Data Index: 632563 (C4 (Web Text))

Max Activating Token Index: 848

Text #7

Max Range: 1.5428. Min Range: -1.5428

Max Act: 1.1420. Min Act: -0.0001

Data Index: 413811 (C4 (Web Text))

Max Activating Token Index: 372

Text #8

Max Range: 1.5428. Min Range: -1.5428

Max Act: 1.2506. Min Act: -0.0000

Data Index: 1064067 (C4 (Web Text))

Max Activating Token Index: 560

Text #9

Max Range: 1.5428. Min Range: -1.5428

Max Act: 1.0773. Min Act: -0.0001

Data Index: 716586 (C4 (Web Text))

Max Activating Token Index: 708

Text #10

Max Range: 1.5428. Min Range: -1.5428

Max Act: 1.1163. Min Act: -0.0000

Data Index: 281917 (C4 (Web Text))

Max Activating Token Index: 764

Text #11

Max Range: 1.5428. Min Range: -1.5428

Max Act: 1.1461. Min Act: -0.0000

Data Index: 357404 (C4 (Web Text))

Max Activating Token Index: 400

Text #12

Max Range: 1.5428. Min Range: -1.5428

Max Act: 1.0301. Min Act: -0.0000

Data Index: 1034628 (C4 (Web Text))

Max Activating Token Index: 330

Text #13

Max Range: 1.5428. Min Range: -1.5428

Max Act: 1.0614. Min Act: -0.0001

Data Index: 603096 (C4 (Web Text))

Max Activating Token Index: 621

Text #14

Max Range: 1.5428. Min Range: -1.5428

Max Act: 0.9971. Min Act: -0.0000

Data Index: 705388 (C4 (Web Text))

Max Activating Token Index: 848

Text #15

Max Range: 1.5428. Min Range: -1.5428

Max Act: 0.9215. Min Act: -0.0000

Data Index: 489032 (C4 (Web Text))

Max Activating Token Index: 67

Text #16

Max Range: 1.5428. Min Range: -1.5428

Max Act: 0.9965. Min Act: -0.0000

Data Index: 1272767 (C4 (Web Text))

Max Activating Token Index: 817

Text #17

Max Range: 1.5428. Min Range: -1.5428

Max Act: 0.9805. Min Act: -0.0000

Data Index: 729849 (C4 (Web Text))

Max Activating Token Index: 383

Text #18

Max Range: 1.5428. Min Range: -1.5428

Max Act: 0.9763. Min Act: -0.0000

Data Index: 488591 (C4 (Web Text))

Max Activating Token Index: 611

Text #19

Max Range: 1.5428. Min Range: -1.5428

Max Act: 0.9151. Min Act: -0.0001

Data Index: 810400 (C4 (Web Text))

Max Activating Token Index: 460