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

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

Neuron 1824 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.2669. Min Range: -4.2669

Max Act: 4.1471. Min Act: -0.0000

Data Index: 833279 (C4 (Web Text))

Max Activating Token Index: 674

Text #1

Max Range: 4.2669. Min Range: -4.2669

Max Act: 3.9239. Min Act: -0.0000

Data Index: 1305650 (C4 (Web Text))

Max Activating Token Index: 634

Text #2

Max Range: 4.2669. Min Range: -4.2669

Max Act: 4.2669. Min Act: -0.0000

Data Index: 1106595 (C4 (Web Text))

Max Activating Token Index: 650

Text #3

Max Range: 4.2669. Min Range: -4.2669

Max Act: 3.6235. Min Act: -0.0000

Data Index: 549989 (C4 (Web Text))

Max Activating Token Index: 294

Text #4

Max Range: 4.2669. Min Range: -4.2669

Max Act: 3.4859. Min Act: -0.0000

Data Index: 1168960 (C4 (Web Text))

Max Activating Token Index: 625

Text #5

Max Range: 4.2669. Min Range: -4.2669

Max Act: 3.4642. Min Act: -0.0000

Data Index: 405556 (C4 (Web Text))

Max Activating Token Index: 882

Text #6

Max Range: 4.2669. Min Range: -4.2669

Max Act: 3.4257. Min Act: -0.0000

Data Index: 103459 (C4 (Web Text))

Max Activating Token Index: 846

Text #7

Max Range: 4.2669. Min Range: -4.2669

Max Act: 3.6269. Min Act: -0.0000

Data Index: 193122 (C4 (Web Text))

Max Activating Token Index: 187

Text #8

Max Range: 4.2669. Min Range: -4.2669

Max Act: 3.5070. Min Act: -0.0000

Data Index: 766944 (C4 (Web Text))

Max Activating Token Index: 353

Text #9

Max Range: 4.2669. Min Range: -4.2669

Max Act: 3.1509. Min Act: -0.0000

Data Index: 686288 (C4 (Web Text))

Max Activating Token Index: 1022

Text #10

Max Range: 4.2669. Min Range: -4.2669

Max Act: 3.4849. Min Act: -0.0000

Data Index: 1175554 (C4 (Web Text))

Max Activating Token Index: 493

Text #11

Max Range: 4.2669. Min Range: -4.2669

Max Act: 3.0693. Min Act: -0.0000

Data Index: 1030969 (C4 (Web Text))

Max Activating Token Index: 775

Text #12

Max Range: 4.2669. Min Range: -4.2669

Max Act: 3.2075. Min Act: -0.0000

Data Index: 606271 (C4 (Web Text))

Max Activating Token Index: 236

Text #13

Max Range: 4.2669. Min Range: -4.2669

Max Act: 3.0477. Min Act: -0.0000

Data Index: 713768 (C4 (Web Text))

Max Activating Token Index: 263

Text #14

Max Range: 4.2669. Min Range: -4.2669

Max Act: 3.2216. Min Act: -0.0000

Data Index: 642491 (C4 (Web Text))

Max Activating Token Index: 207

Text #15

Max Range: 4.2669. Min Range: -4.2669

Max Act: 3.1964. Min Act: -0.0000

Data Index: 701274 (C4 (Web Text))

Max Activating Token Index: 486

Text #16

Max Range: 4.2669. Min Range: -4.2669

Max Act: 2.9899. Min Act: -0.0000

Data Index: 168142 (C4 (Web Text))

Max Activating Token Index: 435

Text #17

Max Range: 4.2669. Min Range: -4.2669

Max Act: 3.1218. Min Act: -0.0000

Data Index: 639098 (C4 (Web Text))

Max Activating Token Index: 600

Text #18

Max Range: 4.2669. Min Range: -4.2669

Max Act: 2.9276. Min Act: -0.0000

Data Index: 145268 (C4 (Web Text))

Max Activating Token Index: 365

Text #19

Max Range: 4.2669. Min Range: -4.2669

Max Act: 2.6202. Min Act: -0.0000

Data Index: 371741 (C4 (Web Text))

Max Activating Token Index: 498