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

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

Neuron 1955 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0405. Min Act: -0.0002

Data Index: 1443686 (Python Code)

Max Activating Token Index: 471

Text #1

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0382. Min Act: -0.0002

Data Index: 210228 (C4 (Web Text))

Max Activating Token Index: 509

Text #2

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0352. Min Act: -0.0002

Data Index: 925127 (C4 (Web Text))

Max Activating Token Index: 426

Text #3

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0340. Min Act: -0.0002

Data Index: 376029 (C4 (Web Text))

Max Activating Token Index: 331

Text #4

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0357. Min Act: -0.0002

Data Index: 326366 (C4 (Web Text))

Max Activating Token Index: 157

Text #5

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0344. Min Act: -0.0002

Data Index: 919992 (C4 (Web Text))

Max Activating Token Index: 852

Text #6

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0324. Min Act: -0.0002

Data Index: 649 (C4 (Web Text))

Max Activating Token Index: 122

Text #7

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0327. Min Act: -0.0002

Data Index: 919828 (C4 (Web Text))

Max Activating Token Index: 719

Text #8

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0320. Min Act: -0.0002

Data Index: 427971 (C4 (Web Text))

Max Activating Token Index: 131

Text #9

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0320. Min Act: -0.0002

Data Index: 1003226 (C4 (Web Text))

Max Activating Token Index: 54

Text #10

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0301. Min Act: -0.0002

Data Index: 611905 (C4 (Web Text))

Max Activating Token Index: 71

Text #11

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0298. Min Act: -0.0002

Data Index: 532436 (C4 (Web Text))

Max Activating Token Index: 533

Text #12

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0288. Min Act: -0.0002

Data Index: 612527 (C4 (Web Text))

Max Activating Token Index: 283

Text #13

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0300. Min Act: -0.0002

Data Index: 981756 (C4 (Web Text))

Max Activating Token Index: 124

Text #14

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0276. Min Act: -0.0002

Data Index: 701757 (C4 (Web Text))

Max Activating Token Index: 231

Text #15

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0291. Min Act: -0.0002

Data Index: 54098 (C4 (Web Text))

Max Activating Token Index: 246

Text #16

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0291. Min Act: -0.0002

Data Index: 72060 (C4 (Web Text))

Max Activating Token Index: 453

Text #17

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0287. Min Act: -0.0002

Data Index: 603835 (C4 (Web Text))

Max Activating Token Index: 716

Text #18

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0284. Min Act: -0.0002

Data Index: 1162059 (C4 (Web Text))

Max Activating Token Index: 529

Text #19

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0278. Min Act: -0.0002

Data Index: 640204 (C4 (Web Text))

Max Activating Token Index: 729