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

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

Neuron 4385 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.0738. Min Range: -6.0738

Max Act: 5.9144. Min Act: -0.0000

Data Index: 1203738 (C4 (Web Text))

Max Activating Token Index: 228

Text #1

Max Range: 6.0738. Min Range: -6.0738

Max Act: 6.0738. Min Act: -0.0000

Data Index: 617476 (C4 (Web Text))

Max Activating Token Index: 214

Text #2

Max Range: 6.0738. Min Range: -6.0738

Max Act: 5.6952. Min Act: -0.0000

Data Index: 1342924 (C4 (Web Text))

Max Activating Token Index: 191

Text #3

Max Range: 6.0738. Min Range: -6.0738

Max Act: 5.6538. Min Act: -0.0000

Data Index: 1288204 (C4 (Web Text))

Max Activating Token Index: 182

Text #4

Max Range: 6.0738. Min Range: -6.0738

Max Act: 5.3382. Min Act: -0.0000

Data Index: 1312528 (C4 (Web Text))

Max Activating Token Index: 218

Text #5

Max Range: 6.0738. Min Range: -6.0738

Max Act: 5.4630. Min Act: -0.0000

Data Index: 429436 (C4 (Web Text))

Max Activating Token Index: 312

Text #6

Max Range: 6.0738. Min Range: -6.0738

Max Act: 5.2678. Min Act: -0.0000

Data Index: 122359 (C4 (Web Text))

Max Activating Token Index: 494

Text #7

Max Range: 6.0738. Min Range: -6.0738

Max Act: 5.4577. Min Act: -0.0000

Data Index: 118649 (C4 (Web Text))

Max Activating Token Index: 338

Text #8

Max Range: 6.0738. Min Range: -6.0738

Max Act: 5.3734. Min Act: -0.0000

Data Index: 411339 (C4 (Web Text))

Max Activating Token Index: 220

Text #9

Max Range: 6.0738. Min Range: -6.0738

Max Act: 5.3413. Min Act: -0.0000

Data Index: 816181 (C4 (Web Text))

Max Activating Token Index: 382

Text #10

Max Range: 6.0738. Min Range: -6.0738

Max Act: 5.1130. Min Act: -0.0000

Data Index: 189879 (C4 (Web Text))

Max Activating Token Index: 307

Text #11

Max Range: 6.0738. Min Range: -6.0738

Max Act: 5.2804. Min Act: -0.0000

Data Index: 697556 (C4 (Web Text))

Max Activating Token Index: 414

Text #12

Max Range: 6.0738. Min Range: -6.0738

Max Act: 5.2871. Min Act: -0.0000

Data Index: 1346517 (C4 (Web Text))

Max Activating Token Index: 454

Text #13

Max Range: 6.0738. Min Range: -6.0738

Max Act: 4.9119. Min Act: -0.0000

Data Index: 771201 (C4 (Web Text))

Max Activating Token Index: 847

Text #14

Max Range: 6.0738. Min Range: -6.0738

Max Act: 5.2578. Min Act: -0.0000

Data Index: 555964 (C4 (Web Text))

Max Activating Token Index: 574

Text #15

Max Range: 6.0738. Min Range: -6.0738

Max Act: 5.0379. Min Act: -0.0000

Data Index: 1298426 (C4 (Web Text))

Max Activating Token Index: 865

Text #16

Max Range: 6.0738. Min Range: -6.0738

Max Act: 5.0654. Min Act: -0.0000

Data Index: 764160 (C4 (Web Text))

Max Activating Token Index: 709

Text #17

Max Range: 6.0738. Min Range: -6.0738

Max Act: 4.9804. Min Act: -0.0000

Data Index: 966739 (C4 (Web Text))

Max Activating Token Index: 402

Text #18

Max Range: 6.0738. Min Range: -6.0738

Max Act: 5.1434. Min Act: -0.0000

Data Index: 1202398 (C4 (Web Text))

Max Activating Token Index: 170

Text #19

Max Range: 6.0738. Min Range: -6.0738

Max Act: 4.9585. Min Act: -0.0000

Data Index: 1252156 (C4 (Web Text))

Max Activating Token Index: 393