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

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

Neuron 4013 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1633. Min Range: -2.1633

Max Act: 2.1633. Min Act: -0.0000

Data Index: 1315273 (C4 (Web Text))

Max Activating Token Index: 262

Text #1

Max Range: 2.1633. Min Range: -2.1633

Max Act: 1.8821. Min Act: -0.0000

Data Index: 983999 (C4 (Web Text))

Max Activating Token Index: 347

Text #2

Max Range: 2.1633. Min Range: -2.1633

Max Act: 1.8725. Min Act: -0.0000

Data Index: 542549 (C4 (Web Text))

Max Activating Token Index: 945

Text #3

Max Range: 2.1633. Min Range: -2.1633

Max Act: 1.8428. Min Act: -0.0000

Data Index: 760386 (C4 (Web Text))

Max Activating Token Index: 93

Text #4

Max Range: 2.1633. Min Range: -2.1633

Max Act: 1.8514. Min Act: -0.0000

Data Index: 242094 (C4 (Web Text))

Max Activating Token Index: 161

Text #5

Max Range: 2.1633. Min Range: -2.1633

Max Act: 1.7519. Min Act: -0.0000

Data Index: 849931 (C4 (Web Text))

Max Activating Token Index: 102

Text #6

Max Range: 2.1633. Min Range: -2.1633

Max Act: 1.8760. Min Act: -0.0000

Data Index: 924502 (C4 (Web Text))

Max Activating Token Index: 613

Text #7

Max Range: 2.1633. Min Range: -2.1633

Max Act: 1.8142. Min Act: -0.0000

Data Index: 202005 (C4 (Web Text))

Max Activating Token Index: 903

Text #8

Max Range: 2.1633. Min Range: -2.1633

Max Act: 1.7685. Min Act: -0.0000

Data Index: 1396487 (Python Code)

Max Activating Token Index: 160

Text #9

Max Range: 2.1633. Min Range: -2.1633

Max Act: 1.6894. Min Act: -0.0000

Data Index: 906992 (C4 (Web Text))

Max Activating Token Index: 166

Text #10

Max Range: 2.1633. Min Range: -2.1633

Max Act: 1.6205. Min Act: -0.0000

Data Index: 521085 (C4 (Web Text))

Max Activating Token Index: 714

Text #11

Max Range: 2.1633. Min Range: -2.1633

Max Act: 1.5684. Min Act: -0.0000

Data Index: 923732 (C4 (Web Text))

Max Activating Token Index: 224

Text #12

Max Range: 2.1633. Min Range: -2.1633

Max Act: 1.6209. Min Act: -0.0000

Data Index: 527234 (C4 (Web Text))

Max Activating Token Index: 409

Text #13

Max Range: 2.1633. Min Range: -2.1633

Max Act: 1.6069. Min Act: -0.0000

Data Index: 438565 (C4 (Web Text))

Max Activating Token Index: 851

Text #14

Max Range: 2.1633. Min Range: -2.1633

Max Act: 1.6382. Min Act: -0.0000

Data Index: 874721 (C4 (Web Text))

Max Activating Token Index: 56

Text #15

Max Range: 2.1633. Min Range: -2.1633

Max Act: 1.6906. Min Act: -0.0000

Data Index: 1311396 (C4 (Web Text))

Max Activating Token Index: 187

Text #16

Max Range: 2.1633. Min Range: -2.1633

Max Act: 1.6301. Min Act: -0.0000

Data Index: 1185576 (C4 (Web Text))

Max Activating Token Index: 970

Text #17

Max Range: 2.1633. Min Range: -2.1633

Max Act: 1.6411. Min Act: -0.0000

Data Index: 996643 (C4 (Web Text))

Max Activating Token Index: 568

Text #18

Max Range: 2.1633. Min Range: -2.1633

Max Act: 1.5488. Min Act: -0.0000

Data Index: 289235 (C4 (Web Text))

Max Activating Token Index: 539

Text #19

Max Range: 2.1633. Min Range: -2.1633

Max Act: 1.5387. Min Act: -0.0000

Data Index: 216103 (C4 (Web Text))

Max Activating Token Index: 143