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

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

Neuron 2325 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8532. Min Range: -1.8532

Max Act: 1.8528. Min Act: -0.0000

Data Index: 1319033 (C4 (Web Text))

Max Activating Token Index: 886

Text #1

Max Range: 1.8532. Min Range: -1.8532

Max Act: 1.7105. Min Act: -0.0000

Data Index: 724653 (C4 (Web Text))

Max Activating Token Index: 49

Text #2

Max Range: 1.8532. Min Range: -1.8532

Max Act: 1.8011. Min Act: -0.0000

Data Index: 1119632 (C4 (Web Text))

Max Activating Token Index: 105

Text #3

Max Range: 1.8532. Min Range: -1.8532

Max Act: 1.8532. Min Act: -0.0000

Data Index: 1271699 (C4 (Web Text))

Max Activating Token Index: 762

Text #4

Max Range: 1.8532. Min Range: -1.8532

Max Act: 1.5624. Min Act: -0.0000

Data Index: 1341982 (C4 (Web Text))

Max Activating Token Index: 383

Text #5

Max Range: 1.8532. Min Range: -1.8532

Max Act: 1.7065. Min Act: -0.0000

Data Index: 130345 (C4 (Web Text))

Max Activating Token Index: 715

Text #6

Max Range: 1.8532. Min Range: -1.8532

Max Act: 1.5270. Min Act: -0.0000

Data Index: 451252 (C4 (Web Text))

Max Activating Token Index: 390

Text #7

Max Range: 1.8532. Min Range: -1.8532

Max Act: 1.6939. Min Act: -0.0000

Data Index: 726440 (C4 (Web Text))

Max Activating Token Index: 104

Text #8

Max Range: 1.8532. Min Range: -1.8532

Max Act: 1.5509. Min Act: -0.0000

Data Index: 148305 (C4 (Web Text))

Max Activating Token Index: 474

Text #9

Max Range: 1.8532. Min Range: -1.8532

Max Act: 1.5373. Min Act: -0.0000

Data Index: 379501 (C4 (Web Text))

Max Activating Token Index: 98

Text #10

Max Range: 1.8532. Min Range: -1.8532

Max Act: 1.6296. Min Act: -0.0000

Data Index: 199009 (C4 (Web Text))

Max Activating Token Index: 769

Text #11

Max Range: 1.8532. Min Range: -1.8532

Max Act: 1.4423. Min Act: -0.0000

Data Index: 90092 (C4 (Web Text))

Max Activating Token Index: 197

Text #12

Max Range: 1.8532. Min Range: -1.8532

Max Act: 1.4531. Min Act: -0.0000

Data Index: 472092 (C4 (Web Text))

Max Activating Token Index: 181

Text #13

Max Range: 1.8532. Min Range: -1.8532

Max Act: 1.4243. Min Act: -0.0000

Data Index: 4081 (C4 (Web Text))

Max Activating Token Index: 193

Text #14

Max Range: 1.8532. Min Range: -1.8532

Max Act: 1.4911. Min Act: -0.0000

Data Index: 1075564 (C4 (Web Text))

Max Activating Token Index: 427

Text #15

Max Range: 1.8532. Min Range: -1.8532

Max Act: 1.3723. Min Act: -0.0000

Data Index: 1162398 (C4 (Web Text))

Max Activating Token Index: 199

Text #16

Max Range: 1.8532. Min Range: -1.8532

Max Act: 1.4845. Min Act: -0.0000

Data Index: 300108 (C4 (Web Text))

Max Activating Token Index: 166

Text #17

Max Range: 1.8532. Min Range: -1.8532

Max Act: 1.5170. Min Act: -0.0000

Data Index: 1303859 (C4 (Web Text))

Max Activating Token Index: 445

Text #18

Max Range: 1.8532. Min Range: -1.8532

Max Act: 1.4098. Min Act: -0.0000

Data Index: 548508 (C4 (Web Text))

Max Activating Token Index: 434

Text #19

Max Range: 1.8532. Min Range: -1.8532

Max Act: 1.5246. Min Act: -0.0000

Data Index: 753839 (C4 (Web Text))

Max Activating Token Index: 221