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

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

Neuron 4805 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9192. Min Range: -1.9192

Max Act: 1.9192. Min Act: -0.0000

Data Index: 847434 (C4 (Web Text))

Max Activating Token Index: 744

Text #1

Max Range: 1.9192. Min Range: -1.9192

Max Act: 1.7487. Min Act: -0.0000

Data Index: 1413359 (Python Code)

Max Activating Token Index: 136

Text #2

Max Range: 1.9192. Min Range: -1.9192

Max Act: 1.5890. Min Act: -0.0000

Data Index: 239572 (C4 (Web Text))

Max Activating Token Index: 103

Text #3

Max Range: 1.9192. Min Range: -1.9192

Max Act: 1.4982. Min Act: -0.0000

Data Index: 523672 (C4 (Web Text))

Max Activating Token Index: 337

Text #4

Max Range: 1.9192. Min Range: -1.9192

Max Act: 1.5059. Min Act: -0.0000

Data Index: 615929 (C4 (Web Text))

Max Activating Token Index: 82

Text #5

Max Range: 1.9192. Min Range: -1.9192

Max Act: 1.6693. Min Act: -0.0000

Data Index: 630265 (C4 (Web Text))

Max Activating Token Index: 80

Text #6

Max Range: 1.9192. Min Range: -1.9192

Max Act: 1.2662. Min Act: -0.0000

Data Index: 699207 (C4 (Web Text))

Max Activating Token Index: 517

Text #7

Max Range: 1.9192. Min Range: -1.9192

Max Act: 1.1161. Min Act: -0.0000

Data Index: 1048808 (C4 (Web Text))

Max Activating Token Index: 724

Text #8

Max Range: 1.9192. Min Range: -1.9192

Max Act: 1.2380. Min Act: -0.0000

Data Index: 672238 (C4 (Web Text))

Max Activating Token Index: 757

Text #9

Max Range: 1.9192. Min Range: -1.9192

Max Act: 1.2712. Min Act: -0.0000

Data Index: 724766 (C4 (Web Text))

Max Activating Token Index: 256

Text #10

Max Range: 1.9192. Min Range: -1.9192

Max Act: 1.1752. Min Act: -0.0000

Data Index: 585505 (C4 (Web Text))

Max Activating Token Index: 410

Text #11

Max Range: 1.9192. Min Range: -1.9192

Max Act: 1.2420. Min Act: -0.0000

Data Index: 442933 (C4 (Web Text))

Max Activating Token Index: 808

Text #12

Max Range: 1.9192. Min Range: -1.9192

Max Act: 1.2240. Min Act: -0.0000

Data Index: 35449 (C4 (Web Text))

Max Activating Token Index: 998

Text #13

Max Range: 1.9192. Min Range: -1.9192

Max Act: 1.1264. Min Act: -0.0000

Data Index: 1501600 (Python Code)

Max Activating Token Index: 252

Text #14

Max Range: 1.9192. Min Range: -1.9192

Max Act: 1.2669. Min Act: -0.0000

Data Index: 928614 (C4 (Web Text))

Max Activating Token Index: 903

Text #15

Max Range: 1.9192. Min Range: -1.9192

Max Act: 1.1932. Min Act: -0.0000

Data Index: 402764 (C4 (Web Text))

Max Activating Token Index: 342

Text #16

Max Range: 1.9192. Min Range: -1.9192

Max Act: 1.1850. Min Act: -0.0000

Data Index: 97283 (C4 (Web Text))

Max Activating Token Index: 514

Text #17

Max Range: 1.9192. Min Range: -1.9192

Max Act: 1.2460. Min Act: -0.0000

Data Index: 150719 (C4 (Web Text))

Max Activating Token Index: 551

Text #18

Max Range: 1.9192. Min Range: -1.9192

Max Act: 1.1870. Min Act: -0.0000

Data Index: 123619 (C4 (Web Text))

Max Activating Token Index: 364

Text #19

Max Range: 1.9192. Min Range: -1.9192

Max Act: 1.0920. Min Act: -0.0000

Data Index: 1206692 (C4 (Web Text))

Max Activating Token Index: 253