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

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

Neuron 2720 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5543. Min Range: -0.5543

Max Act: 0.5543. Min Act: -0.0000

Data Index: 634477 (C4 (Web Text))

Max Activating Token Index: 417

Text #1

Max Range: 0.5543. Min Range: -0.5543

Max Act: 0.5225. Min Act: -0.0000

Data Index: 258442 (C4 (Web Text))

Max Activating Token Index: 242

Text #2

Max Range: 0.5543. Min Range: -0.5543

Max Act: 0.5371. Min Act: -0.0000

Data Index: 877930 (C4 (Web Text))

Max Activating Token Index: 532

Text #3

Max Range: 0.5543. Min Range: -0.5543

Max Act: 0.5030. Min Act: -0.0000

Data Index: 5210 (C4 (Web Text))

Max Activating Token Index: 323

Text #4

Max Range: 0.5543. Min Range: -0.5543

Max Act: 0.4718. Min Act: -0.0000

Data Index: 321554 (C4 (Web Text))

Max Activating Token Index: 1004

Text #5

Max Range: 0.5543. Min Range: -0.5543

Max Act: 0.4671. Min Act: -0.0000

Data Index: 540698 (C4 (Web Text))

Max Activating Token Index: 466

Text #6

Max Range: 0.5543. Min Range: -0.5543

Max Act: 0.4442. Min Act: -0.0000

Data Index: 78749 (C4 (Web Text))

Max Activating Token Index: 22

Text #7

Max Range: 0.5543. Min Range: -0.5543

Max Act: 0.4654. Min Act: -0.0000

Data Index: 83310 (C4 (Web Text))

Max Activating Token Index: 582

Text #8

Max Range: 0.5543. Min Range: -0.5543

Max Act: 0.4624. Min Act: -0.0000

Data Index: 1087294 (C4 (Web Text))

Max Activating Token Index: 579

Text #9

Max Range: 0.5543. Min Range: -0.5543

Max Act: 0.4190. Min Act: -0.0000

Data Index: 1088027 (C4 (Web Text))

Max Activating Token Index: 978

Text #10

Max Range: 0.5543. Min Range: -0.5543

Max Act: 0.4412. Min Act: -0.0000

Data Index: 845721 (C4 (Web Text))

Max Activating Token Index: 273

Text #11

Max Range: 0.5543. Min Range: -0.5543

Max Act: 0.4246. Min Act: -0.0000

Data Index: 130366 (C4 (Web Text))

Max Activating Token Index: 71

Text #12

Max Range: 0.5543. Min Range: -0.5543

Max Act: 0.3962. Min Act: -0.0000

Data Index: 655005 (C4 (Web Text))

Max Activating Token Index: 520

Text #13

Max Range: 0.5543. Min Range: -0.5543

Max Act: 0.4315. Min Act: -0.0000

Data Index: 166338 (C4 (Web Text))

Max Activating Token Index: 552

Text #14

Max Range: 0.5543. Min Range: -0.5543

Max Act: 0.4038. Min Act: -0.0000

Data Index: 49538 (C4 (Web Text))

Max Activating Token Index: 861

Text #15

Max Range: 0.5543. Min Range: -0.5543

Max Act: 0.4133. Min Act: -0.0000

Data Index: 861269 (C4 (Web Text))

Max Activating Token Index: 959

Text #16

Max Range: 0.5543. Min Range: -0.5543

Max Act: 0.3826. Min Act: -0.0000

Data Index: 482301 (C4 (Web Text))

Max Activating Token Index: 393

Text #17

Max Range: 0.5543. Min Range: -0.5543

Max Act: 0.3970. Min Act: 0.0000

Data Index: 453442 (C4 (Web Text))

Max Activating Token Index: 165

Text #18

Max Range: 0.5543. Min Range: -0.5543

Max Act: 0.4192. Min Act: -0.0000

Data Index: 1212637 (C4 (Web Text))

Max Activating Token Index: 626

Text #19

Max Range: 0.5543. Min Range: -0.5543

Max Act: 0.4027. Min Act: -0.0000

Data Index: 695069 (C4 (Web Text))

Max Activating Token Index: 780