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

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

Neuron 1408 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: 2.4580. Min Range: -2.4580

Max Act: 2.4580. Min Act: -0.0000

Data Index: 725968 (C4 (Web Text))

Max Activating Token Index: 640

Text #1

Max Range: 2.4580. Min Range: -2.4580

Max Act: 2.4441. Min Act: -0.0000

Data Index: 987856 (C4 (Web Text))

Max Activating Token Index: 893

Text #2

Max Range: 2.4580. Min Range: -2.4580

Max Act: 2.4518. Min Act: -0.0000

Data Index: 215634 (C4 (Web Text))

Max Activating Token Index: 209

Text #3

Max Range: 2.4580. Min Range: -2.4580

Max Act: 2.2759. Min Act: -0.0000

Data Index: 11755 (C4 (Web Text))

Max Activating Token Index: 802

Text #4

Max Range: 2.4580. Min Range: -2.4580

Max Act: 2.3938. Min Act: -0.0000

Data Index: 394201 (C4 (Web Text))

Max Activating Token Index: 1001

Text #5

Max Range: 2.4580. Min Range: -2.4580

Max Act: 2.3253. Min Act: -0.0000

Data Index: 468451 (C4 (Web Text))

Max Activating Token Index: 312

Text #6

Max Range: 2.4580. Min Range: -2.4580

Max Act: 2.2770. Min Act: -0.0000

Data Index: 71664 (C4 (Web Text))

Max Activating Token Index: 474

Text #7

Max Range: 2.4580. Min Range: -2.4580

Max Act: 2.1294. Min Act: -0.0000

Data Index: 878401 (C4 (Web Text))

Max Activating Token Index: 366

Text #8

Max Range: 2.4580. Min Range: -2.4580

Max Act: 2.1019. Min Act: -0.0000

Data Index: 963655 (C4 (Web Text))

Max Activating Token Index: 593

Text #9

Max Range: 2.4580. Min Range: -2.4580

Max Act: 2.0711. Min Act: -0.0000

Data Index: 872012 (C4 (Web Text))

Max Activating Token Index: 886

Text #10

Max Range: 2.4580. Min Range: -2.4580

Max Act: 2.2994. Min Act: -0.0000

Data Index: 88325 (C4 (Web Text))

Max Activating Token Index: 123

Text #11

Max Range: 2.4580. Min Range: -2.4580

Max Act: 2.0536. Min Act: -0.0000

Data Index: 79467 (C4 (Web Text))

Max Activating Token Index: 842

Text #12

Max Range: 2.4580. Min Range: -2.4580

Max Act: 2.0140. Min Act: -0.0000

Data Index: 733412 (C4 (Web Text))

Max Activating Token Index: 851

Text #13

Max Range: 2.4580. Min Range: -2.4580

Max Act: 2.2423. Min Act: -0.0000

Data Index: 73444 (C4 (Web Text))

Max Activating Token Index: 606

Text #14

Max Range: 2.4580. Min Range: -2.4580

Max Act: 2.1858. Min Act: -0.0000

Data Index: 667261 (C4 (Web Text))

Max Activating Token Index: 187

Text #15

Max Range: 2.4580. Min Range: -2.4580

Max Act: 1.9802. Min Act: -0.0000

Data Index: 165393 (C4 (Web Text))

Max Activating Token Index: 302

Text #16

Max Range: 2.4580. Min Range: -2.4580

Max Act: 2.0592. Min Act: -0.0000

Data Index: 1316429 (C4 (Web Text))

Max Activating Token Index: 598

Text #17

Max Range: 2.4580. Min Range: -2.4580

Max Act: 2.0786. Min Act: -0.0000

Data Index: 1330815 (C4 (Web Text))

Max Activating Token Index: 596

Text #18

Max Range: 2.4580. Min Range: -2.4580

Max Act: 2.1675. Min Act: -0.0000

Data Index: 4852 (C4 (Web Text))

Max Activating Token Index: 365

Text #19

Max Range: 2.4580. Min Range: -2.4580

Max Act: 2.0633. Min Act: -0.0000

Data Index: 983775 (C4 (Web Text))

Max Activating Token Index: 63