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

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

Neuron 3075 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9672. Min Range: -2.9672

Max Act: 2.9672. Min Act: -0.0000

Data Index: 1205852 (C4 (Web Text))

Max Activating Token Index: 617

Text #1

Max Range: 2.9672. Min Range: -2.9672

Max Act: 2.8094. Min Act: -0.0000

Data Index: 1282777 (C4 (Web Text))

Max Activating Token Index: 262

Text #2

Max Range: 2.9672. Min Range: -2.9672

Max Act: 2.6380. Min Act: -0.0000

Data Index: 943944 (C4 (Web Text))

Max Activating Token Index: 372

Text #3

Max Range: 2.9672. Min Range: -2.9672

Max Act: 2.5562. Min Act: -0.0000

Data Index: 577531 (C4 (Web Text))

Max Activating Token Index: 477

Text #4

Max Range: 2.9672. Min Range: -2.9672

Max Act: 2.5025. Min Act: -0.0000

Data Index: 903083 (C4 (Web Text))

Max Activating Token Index: 342

Text #5

Max Range: 2.9672. Min Range: -2.9672

Max Act: 2.3659. Min Act: -0.0000

Data Index: 928142 (C4 (Web Text))

Max Activating Token Index: 651

Text #6

Max Range: 2.9672. Min Range: -2.9672

Max Act: 2.3380. Min Act: -0.0000

Data Index: 337548 (C4 (Web Text))

Max Activating Token Index: 226

Text #7

Max Range: 2.9672. Min Range: -2.9672

Max Act: 2.2878. Min Act: -0.0000

Data Index: 1353035 (C4 (Web Text))

Max Activating Token Index: 534

Text #8

Max Range: 2.9672. Min Range: -2.9672

Max Act: 2.1373. Min Act: -0.0000

Data Index: 1343895 (C4 (Web Text))

Max Activating Token Index: 421

Text #9

Max Range: 2.9672. Min Range: -2.9672

Max Act: 2.1106. Min Act: -0.0000

Data Index: 724596 (C4 (Web Text))

Max Activating Token Index: 836

Text #10

Max Range: 2.9672. Min Range: -2.9672

Max Act: 2.2274. Min Act: -0.0000

Data Index: 140632 (C4 (Web Text))

Max Activating Token Index: 87

Text #11

Max Range: 2.9672. Min Range: -2.9672

Max Act: 2.2825. Min Act: -0.0000

Data Index: 1298572 (C4 (Web Text))

Max Activating Token Index: 945

Text #12

Max Range: 2.9672. Min Range: -2.9672

Max Act: 2.1630. Min Act: -0.0000

Data Index: 391283 (C4 (Web Text))

Max Activating Token Index: 530

Text #13

Max Range: 2.9672. Min Range: -2.9672

Max Act: 2.1241. Min Act: -0.0000

Data Index: 693990 (C4 (Web Text))

Max Activating Token Index: 966

Text #14

Max Range: 2.9672. Min Range: -2.9672

Max Act: 2.0607. Min Act: -0.0000

Data Index: 701430 (C4 (Web Text))

Max Activating Token Index: 407

Text #15

Max Range: 2.9672. Min Range: -2.9672

Max Act: 2.1420. Min Act: -0.0000

Data Index: 512887 (C4 (Web Text))

Max Activating Token Index: 795

Text #16

Max Range: 2.9672. Min Range: -2.9672

Max Act: 2.0235. Min Act: -0.0000

Data Index: 639345 (C4 (Web Text))

Max Activating Token Index: 438

Text #17

Max Range: 2.9672. Min Range: -2.9672

Max Act: 1.8981. Min Act: -0.0000

Data Index: 967324 (C4 (Web Text))

Max Activating Token Index: 687

Text #18

Max Range: 2.9672. Min Range: -2.9672

Max Act: 1.9925. Min Act: 0.0001

Data Index: 369982 (C4 (Web Text))

Max Activating Token Index: 25

Text #19

Max Range: 2.9672. Min Range: -2.9672

Max Act: 1.9822. Min Act: -0.0000

Data Index: 739823 (C4 (Web Text))

Max Activating Token Index: 119