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

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

Neuron 1742 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3521. Min Range: -0.3521

Max Act: 0.3521. Min Act: -0.0000

Data Index: 570048 (C4 (Web Text))

Max Activating Token Index: 114

Text #1

Max Range: 0.3521. Min Range: -0.3521

Max Act: 0.2703. Min Act: -0.0001

Data Index: 700208 (C4 (Web Text))

Max Activating Token Index: 910

Text #2

Max Range: 0.3521. Min Range: -0.3521

Max Act: 0.2980. Min Act: -0.0001

Data Index: 118165 (C4 (Web Text))

Max Activating Token Index: 761

Text #3

Max Range: 0.3521. Min Range: -0.3521

Max Act: 0.2501. Min Act: -0.0000

Data Index: 67906 (C4 (Web Text))

Max Activating Token Index: 211

Text #4

Max Range: 0.3521. Min Range: -0.3521

Max Act: 0.2583. Min Act: -0.0001

Data Index: 648216 (C4 (Web Text))

Max Activating Token Index: 642

Text #5

Max Range: 0.3521. Min Range: -0.3521

Max Act: 0.2469. Min Act: -0.0000

Data Index: 989845 (C4 (Web Text))

Max Activating Token Index: 639

Text #6

Max Range: 0.3521. Min Range: -0.3521

Max Act: 0.2395. Min Act: -0.0000

Data Index: 609185 (C4 (Web Text))

Max Activating Token Index: 593

Text #7

Max Range: 0.3521. Min Range: -0.3521

Max Act: 0.2378. Min Act: -0.0001

Data Index: 182910 (C4 (Web Text))

Max Activating Token Index: 96

Text #8

Max Range: 0.3521. Min Range: -0.3521

Max Act: 0.2341. Min Act: -0.0001

Data Index: 1347951 (C4 (Web Text))

Max Activating Token Index: 284

Text #9

Max Range: 0.3521. Min Range: -0.3521

Max Act: 0.2288. Min Act: -0.0000

Data Index: 1300199 (C4 (Web Text))

Max Activating Token Index: 428

Text #10

Max Range: 0.3521. Min Range: -0.3521

Max Act: 0.2274. Min Act: -0.0001

Data Index: 302298 (C4 (Web Text))

Max Activating Token Index: 163

Text #11

Max Range: 0.3521. Min Range: -0.3521

Max Act: 0.1793. Min Act: -0.0001

Data Index: 606200 (C4 (Web Text))

Max Activating Token Index: 517

Text #12

Max Range: 0.3521. Min Range: -0.3521

Max Act: 0.1993. Min Act: -0.0001

Data Index: 929584 (C4 (Web Text))

Max Activating Token Index: 550

Text #13

Max Range: 0.3521. Min Range: -0.3521

Max Act: 0.2421. Min Act: -0.0001

Data Index: 325699 (C4 (Web Text))

Max Activating Token Index: 241

Text #14

Max Range: 0.3521. Min Range: -0.3521

Max Act: 0.2101. Min Act: -0.0001

Data Index: 350291 (C4 (Web Text))

Max Activating Token Index: 245

Text #15

Max Range: 0.3521. Min Range: -0.3521

Max Act: 0.2163. Min Act: -0.0001

Data Index: 1380874 (Python Code)

Max Activating Token Index: 960

Text #16

Max Range: 0.3521. Min Range: -0.3521

Max Act: 0.2047. Min Act: -0.0000

Data Index: 1100578 (C4 (Web Text))

Max Activating Token Index: 902

Text #17

Max Range: 0.3521. Min Range: -0.3521

Max Act: 0.1951. Min Act: -0.0000

Data Index: 98045 (C4 (Web Text))

Max Activating Token Index: 826

Text #18

Max Range: 0.3521. Min Range: -0.3521

Max Act: 0.2108. Min Act: -0.0000

Data Index: 374446 (C4 (Web Text))

Max Activating Token Index: 289

Text #19

Max Range: 0.3521. Min Range: -0.3521

Max Act: 0.2131. Min Act: -0.0001

Data Index: 352970 (C4 (Web Text))

Max Activating Token Index: 538