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

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

Neuron 5046 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.0974. Min Range: -1.0974

Max Act: 1.0657. Min Act: -0.0000

Data Index: 627420 (C4 (Web Text))

Max Activating Token Index: 859

Text #1

Max Range: 1.0974. Min Range: -1.0974

Max Act: 0.9110. Min Act: -0.0000

Data Index: 164566 (C4 (Web Text))

Max Activating Token Index: 766

Text #2

Max Range: 1.0974. Min Range: -1.0974

Max Act: 0.9473. Min Act: -0.0000

Data Index: 691349 (C4 (Web Text))

Max Activating Token Index: 687

Text #3

Max Range: 1.0974. Min Range: -1.0974

Max Act: 1.0974. Min Act: -0.0000

Data Index: 26224 (C4 (Web Text))

Max Activating Token Index: 658

Text #4

Max Range: 1.0974. Min Range: -1.0974

Max Act: 0.9535. Min Act: -0.0000

Data Index: 818907 (C4 (Web Text))

Max Activating Token Index: 201

Text #5

Max Range: 1.0974. Min Range: -1.0974

Max Act: 0.9149. Min Act: -0.0000

Data Index: 59389 (C4 (Web Text))

Max Activating Token Index: 312

Text #6

Max Range: 1.0974. Min Range: -1.0974

Max Act: 0.8934. Min Act: -0.0001

Data Index: 1127450 (C4 (Web Text))

Max Activating Token Index: 752

Text #7

Max Range: 1.0974. Min Range: -1.0974

Max Act: 0.9290. Min Act: -0.0000

Data Index: 722592 (C4 (Web Text))

Max Activating Token Index: 518

Text #8

Max Range: 1.0974. Min Range: -1.0974

Max Act: 0.8430. Min Act: -0.0000

Data Index: 194110 (C4 (Web Text))

Max Activating Token Index: 886

Text #9

Max Range: 1.0974. Min Range: -1.0974

Max Act: 0.8254. Min Act: -0.0000

Data Index: 494270 (C4 (Web Text))

Max Activating Token Index: 84

Text #10

Max Range: 1.0974. Min Range: -1.0974

Max Act: 0.8752. Min Act: -0.0001

Data Index: 1163664 (C4 (Web Text))

Max Activating Token Index: 376

Text #11

Max Range: 1.0974. Min Range: -1.0974

Max Act: 0.8303. Min Act: -0.0000

Data Index: 256135 (C4 (Web Text))

Max Activating Token Index: 189

Text #12

Max Range: 1.0974. Min Range: -1.0974

Max Act: 0.8633. Min Act: -0.0000

Data Index: 783237 (C4 (Web Text))

Max Activating Token Index: 600

Text #13

Max Range: 1.0974. Min Range: -1.0974

Max Act: 0.8453. Min Act: -0.0000

Data Index: 32005 (C4 (Web Text))

Max Activating Token Index: 456

Text #14

Max Range: 1.0974. Min Range: -1.0974

Max Act: 0.8098. Min Act: -0.0000

Data Index: 1291788 (C4 (Web Text))

Max Activating Token Index: 253

Text #15

Max Range: 1.0974. Min Range: -1.0974

Max Act: 0.7792. Min Act: -0.0000

Data Index: 1247956 (C4 (Web Text))

Max Activating Token Index: 1020

Text #16

Max Range: 1.0974. Min Range: -1.0974

Max Act: 0.8796. Min Act: -0.0000

Data Index: 207649 (C4 (Web Text))

Max Activating Token Index: 426

Text #17

Max Range: 1.0974. Min Range: -1.0974

Max Act: 0.7861. Min Act: -0.0000

Data Index: 462640 (C4 (Web Text))

Max Activating Token Index: 1019

Text #18

Max Range: 1.0974. Min Range: -1.0974

Max Act: 0.8560. Min Act: -0.0001

Data Index: 396534 (C4 (Web Text))

Max Activating Token Index: 318

Text #19

Max Range: 1.0974. Min Range: -1.0974

Max Act: 0.8192. Min Act: -0.0000

Data Index: 338580 (C4 (Web Text))

Max Activating Token Index: 142