Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1132 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0577. Min Act: -0.0002

Data Index: 1324687 (C4 (Web Text))

Max Activating Token Index: 144

Text #1

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0554. Min Act: -0.0003

Data Index: 953624 (C4 (Web Text))

Max Activating Token Index: 85

Text #2

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0542. Min Act: -0.0003

Data Index: 1101292 (C4 (Web Text))

Max Activating Token Index: 683

Text #3

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0526. Min Act: -0.0003

Data Index: 922918 (C4 (Web Text))

Max Activating Token Index: 52

Text #4

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0519. Min Act: -0.0003

Data Index: 1059833 (C4 (Web Text))

Max Activating Token Index: 244

Text #5

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0497. Min Act: -0.0003

Data Index: 1338752 (C4 (Web Text))

Max Activating Token Index: 555

Text #6

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0485. Min Act: -0.0003

Data Index: 853957 (C4 (Web Text))

Max Activating Token Index: 278

Text #7

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0501. Min Act: -0.0002

Data Index: 953192 (C4 (Web Text))

Max Activating Token Index: 509

Text #8

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0489. Min Act: -0.0003

Data Index: 290231 (C4 (Web Text))

Max Activating Token Index: 48

Text #9

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0488. Min Act: -0.0003

Data Index: 398854 (C4 (Web Text))

Max Activating Token Index: 587

Text #10

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0482. Min Act: -0.0003

Data Index: 534136 (C4 (Web Text))

Max Activating Token Index: 876

Text #11

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0481. Min Act: -0.0003

Data Index: 1284664 (C4 (Web Text))

Max Activating Token Index: 797

Text #12

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0477. Min Act: -0.0003

Data Index: 444418 (C4 (Web Text))

Max Activating Token Index: 69

Text #13

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0475. Min Act: -0.0003

Data Index: 804697 (C4 (Web Text))

Max Activating Token Index: 76

Text #14

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0470. Min Act: -0.0003

Data Index: 1341253 (C4 (Web Text))

Max Activating Token Index: 615

Text #15

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0466. Min Act: -0.0002

Data Index: 542309 (C4 (Web Text))

Max Activating Token Index: 111

Text #16

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0466. Min Act: -0.0003

Data Index: 239911 (C4 (Web Text))

Max Activating Token Index: 994

Text #17

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0464. Min Act: -0.0003

Data Index: 688605 (C4 (Web Text))

Max Activating Token Index: 634

Text #18

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0463. Min Act: -0.0003

Data Index: 578598 (C4 (Web Text))

Max Activating Token Index: 28

Text #19

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0461. Min Act: -0.0003

Data Index: 147148 (C4 (Web Text))

Max Activating Token Index: 596