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

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

Neuron 4361 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1705. Min Range: -3.1705

Max Act: 3.1705. Min Act: -0.0000

Data Index: 585686 (C4 (Web Text))

Max Activating Token Index: 325

Text #1

Max Range: 3.1705. Min Range: -3.1705

Max Act: 1.9918. Min Act: -0.0000

Data Index: 389715 (C4 (Web Text))

Max Activating Token Index: 267

Text #2

Max Range: 3.1705. Min Range: -3.1705

Max Act: 2.2730. Min Act: -0.0000

Data Index: 1334309 (C4 (Web Text))

Max Activating Token Index: 965

Text #3

Max Range: 3.1705. Min Range: -3.1705

Max Act: 2.2224. Min Act: -0.0000

Data Index: 318665 (C4 (Web Text))

Max Activating Token Index: 836

Text #4

Max Range: 3.1705. Min Range: -3.1705

Max Act: 2.1323. Min Act: -0.0000

Data Index: 871681 (C4 (Web Text))

Max Activating Token Index: 632

Text #5

Max Range: 3.1705. Min Range: -3.1705

Max Act: 2.0070. Min Act: -0.0000

Data Index: 1068628 (C4 (Web Text))

Max Activating Token Index: 808

Text #6

Max Range: 3.1705. Min Range: -3.1705

Max Act: 1.8419. Min Act: -0.0000

Data Index: 655327 (C4 (Web Text))

Max Activating Token Index: 195

Text #7

Max Range: 3.1705. Min Range: -3.1705

Max Act: 1.7950. Min Act: -0.0000

Data Index: 1221537 (C4 (Web Text))

Max Activating Token Index: 620

Text #8

Max Range: 3.1705. Min Range: -3.1705

Max Act: 1.9994. Min Act: -0.0001

Data Index: 1202335 (C4 (Web Text))

Max Activating Token Index: 783

Text #9

Max Range: 3.1705. Min Range: -3.1705

Max Act: 1.8412. Min Act: -0.0000

Data Index: 639545 (C4 (Web Text))

Max Activating Token Index: 349

Text #10

Max Range: 3.1705. Min Range: -3.1705

Max Act: 1.9782. Min Act: -0.0000

Data Index: 589561 (C4 (Web Text))

Max Activating Token Index: 328

Text #11

Max Range: 3.1705. Min Range: -3.1705

Max Act: 1.8585. Min Act: -0.0000

Data Index: 956235 (C4 (Web Text))

Max Activating Token Index: 371

Text #12

Max Range: 3.1705. Min Range: -3.1705

Max Act: 1.8269. Min Act: -0.0000

Data Index: 646719 (C4 (Web Text))

Max Activating Token Index: 923

Text #13

Max Range: 3.1705. Min Range: -3.1705

Max Act: 1.8946. Min Act: -0.0000

Data Index: 385117 (C4 (Web Text))

Max Activating Token Index: 111

Text #14

Max Range: 3.1705. Min Range: -3.1705

Max Act: 1.8594. Min Act: -0.0000

Data Index: 1599402 (Python Code)

Max Activating Token Index: 405

Text #15

Max Range: 3.1705. Min Range: -3.1705

Max Act: 1.8617. Min Act: -0.0000

Data Index: 579529 (C4 (Web Text))

Max Activating Token Index: 352

Text #16

Max Range: 3.1705. Min Range: -3.1705

Max Act: 1.8380. Min Act: -0.0000

Data Index: 358432 (C4 (Web Text))

Max Activating Token Index: 996

Text #17

Max Range: 3.1705. Min Range: -3.1705

Max Act: 1.7493. Min Act: -0.0000

Data Index: 363250 (C4 (Web Text))

Max Activating Token Index: 944

Text #18

Max Range: 3.1705. Min Range: -3.1705

Max Act: 1.9915. Min Act: -0.0000

Data Index: 774629 (C4 (Web Text))

Max Activating Token Index: 294

Text #19

Max Range: 3.1705. Min Range: -3.1705

Max Act: 1.9909. Min Act: -0.0000

Data Index: 600936 (C4 (Web Text))

Max Activating Token Index: 333