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

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

Neuron 3968 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7573. Min Range: -0.7573

Max Act: 0.7533. Min Act: -0.0000

Data Index: 944904 (C4 (Web Text))

Max Activating Token Index: 113

Text #1

Max Range: 0.7573. Min Range: -0.7573

Max Act: 0.7573. Min Act: -0.0000

Data Index: 285133 (C4 (Web Text))

Max Activating Token Index: 517

Text #2

Max Range: 0.7573. Min Range: -0.7573

Max Act: 0.7178. Min Act: -0.0000

Data Index: 338891 (C4 (Web Text))

Max Activating Token Index: 855

Text #3

Max Range: 0.7573. Min Range: -0.7573

Max Act: 0.7040. Min Act: -0.0001

Data Index: 470870 (C4 (Web Text))

Max Activating Token Index: 778

Text #4

Max Range: 0.7573. Min Range: -0.7573

Max Act: 0.6514. Min Act: -0.0000

Data Index: 320363 (C4 (Web Text))

Max Activating Token Index: 269

Text #5

Max Range: 0.7573. Min Range: -0.7573

Max Act: 0.6416. Min Act: -0.0000

Data Index: 235281 (C4 (Web Text))

Max Activating Token Index: 879

Text #6

Max Range: 0.7573. Min Range: -0.7573

Max Act: 0.6055. Min Act: -0.0000

Data Index: 1018354 (C4 (Web Text))

Max Activating Token Index: 631

Text #7

Max Range: 0.7573. Min Range: -0.7573

Max Act: 0.6170. Min Act: -0.0000

Data Index: 300621 (C4 (Web Text))

Max Activating Token Index: 262

Text #8

Max Range: 0.7573. Min Range: -0.7573

Max Act: 0.5781. Min Act: -0.0000

Data Index: 1171298 (C4 (Web Text))

Max Activating Token Index: 174

Text #9

Max Range: 0.7573. Min Range: -0.7573

Max Act: 0.5665. Min Act: -0.0000

Data Index: 1246347 (C4 (Web Text))

Max Activating Token Index: 258

Text #10

Max Range: 0.7573. Min Range: -0.7573

Max Act: 0.5750. Min Act: -0.0000

Data Index: 51650 (C4 (Web Text))

Max Activating Token Index: 827

Text #11

Max Range: 0.7573. Min Range: -0.7573

Max Act: 0.5646. Min Act: -0.0000

Data Index: 1255935 (C4 (Web Text))

Max Activating Token Index: 398

Text #12

Max Range: 0.7573. Min Range: -0.7573

Max Act: 0.5383. Min Act: -0.0000

Data Index: 209761 (C4 (Web Text))

Max Activating Token Index: 643

Text #13

Max Range: 0.7573. Min Range: -0.7573

Max Act: 0.5478. Min Act: -0.0001

Data Index: 1306827 (C4 (Web Text))

Max Activating Token Index: 135

Text #14

Max Range: 0.7573. Min Range: -0.7573

Max Act: 0.5469. Min Act: -0.0001

Data Index: 377616 (C4 (Web Text))

Max Activating Token Index: 621

Text #15

Max Range: 0.7573. Min Range: -0.7573

Max Act: 0.5142. Min Act: -0.0001

Data Index: 87985 (C4 (Web Text))

Max Activating Token Index: 469

Text #16

Max Range: 0.7573. Min Range: -0.7573

Max Act: 0.5101. Min Act: -0.0000

Data Index: 333808 (C4 (Web Text))

Max Activating Token Index: 479

Text #17

Max Range: 0.7573. Min Range: -0.7573

Max Act: 0.4936. Min Act: -0.0001

Data Index: 1188911 (C4 (Web Text))

Max Activating Token Index: 364

Text #18

Max Range: 0.7573. Min Range: -0.7573

Max Act: 0.5199. Min Act: -0.0000

Data Index: 249650 (C4 (Web Text))

Max Activating Token Index: 1013

Text #19

Max Range: 0.7573. Min Range: -0.7573

Max Act: 0.5013. Min Act: -0.0000

Data Index: 947474 (C4 (Web Text))

Max Activating Token Index: 910