Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5400 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.7150. Min Range: -0.7150

Max Act: 0.7150. Min Act: -0.0000

Data Index: 781574 (C4 (Web Text))

Max Activating Token Index: 263

Text #1

Max Range: 0.7150. Min Range: -0.7150

Max Act: 0.6877. Min Act: -0.0000

Data Index: 330309 (C4 (Web Text))

Max Activating Token Index: 504

Text #2

Max Range: 0.7150. Min Range: -0.7150

Max Act: 0.7149. Min Act: -0.0000

Data Index: 865559 (C4 (Web Text))

Max Activating Token Index: 762

Text #3

Max Range: 0.7150. Min Range: -0.7150

Max Act: 0.6300. Min Act: -0.0000

Data Index: 564935 (C4 (Web Text))

Max Activating Token Index: 15

Text #4

Max Range: 0.7150. Min Range: -0.7150

Max Act: 0.6413. Min Act: -0.0000

Data Index: 698348 (C4 (Web Text))

Max Activating Token Index: 119

Text #5

Max Range: 0.7150. Min Range: -0.7150

Max Act: 0.6477. Min Act: -0.0000

Data Index: 1244975 (C4 (Web Text))

Max Activating Token Index: 601

Text #6

Max Range: 0.7150. Min Range: -0.7150

Max Act: 0.5931. Min Act: -0.0000

Data Index: 834155 (C4 (Web Text))

Max Activating Token Index: 433

Text #7

Max Range: 0.7150. Min Range: -0.7150

Max Act: 0.6104. Min Act: -0.0000

Data Index: 299785 (C4 (Web Text))

Max Activating Token Index: 997

Text #8

Max Range: 0.7150. Min Range: -0.7150

Max Act: 0.5999. Min Act: -0.0000

Data Index: 973689 (C4 (Web Text))

Max Activating Token Index: 135

Text #9

Max Range: 0.7150. Min Range: -0.7150

Max Act: 0.5898. Min Act: -0.0000

Data Index: 858607 (C4 (Web Text))

Max Activating Token Index: 542

Text #10

Max Range: 0.7150. Min Range: -0.7150

Max Act: 0.6222. Min Act: -0.0000

Data Index: 1202514 (C4 (Web Text))

Max Activating Token Index: 814

Text #11

Max Range: 0.7150. Min Range: -0.7150

Max Act: 0.5837. Min Act: -0.0000

Data Index: 845064 (C4 (Web Text))

Max Activating Token Index: 169

Text #12

Max Range: 0.7150. Min Range: -0.7150

Max Act: 0.5449. Min Act: -0.0000

Data Index: 1255219 (C4 (Web Text))

Max Activating Token Index: 878

Text #13

Max Range: 0.7150. Min Range: -0.7150

Max Act: 0.5851. Min Act: -0.0000

Data Index: 752252 (C4 (Web Text))

Max Activating Token Index: 220

Text #14

Max Range: 0.7150. Min Range: -0.7150

Max Act: 0.5649. Min Act: -0.0000

Data Index: 1133563 (C4 (Web Text))

Max Activating Token Index: 347

Text #15

Max Range: 0.7150. Min Range: -0.7150

Max Act: 0.5635. Min Act: -0.0000

Data Index: 1059329 (C4 (Web Text))

Max Activating Token Index: 549

Text #16

Max Range: 0.7150. Min Range: -0.7150

Max Act: 0.5755. Min Act: -0.0000

Data Index: 564582 (C4 (Web Text))

Max Activating Token Index: 221

Text #17

Max Range: 0.7150. Min Range: -0.7150

Max Act: 0.5382. Min Act: -0.0000

Data Index: 449269 (C4 (Web Text))

Max Activating Token Index: 327

Text #18

Max Range: 0.7150. Min Range: -0.7150

Max Act: 0.5346. Min Act: -0.0000

Data Index: 182330 (C4 (Web Text))

Max Activating Token Index: 760

Text #19

Max Range: 0.7150. Min Range: -0.7150

Max Act: 0.5164. Min Act: -0.0000

Data Index: 416715 (C4 (Web Text))

Max Activating Token Index: 228