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

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

Neuron 1264 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: 0.8828. Min Range: -0.8828

Max Act: 0.8828. Min Act: -0.0000

Data Index: 243124 (C4 (Web Text))

Max Activating Token Index: 1012

Text #1

Max Range: 0.8828. Min Range: -0.8828

Max Act: 0.7110. Min Act: -0.0000

Data Index: 804276 (C4 (Web Text))

Max Activating Token Index: 279

Text #2

Max Range: 0.8828. Min Range: -0.8828

Max Act: 0.5963. Min Act: -0.0000

Data Index: 411039 (C4 (Web Text))

Max Activating Token Index: 330

Text #3

Max Range: 0.8828. Min Range: -0.8828

Max Act: 0.5974. Min Act: -0.0000

Data Index: 266908 (C4 (Web Text))

Max Activating Token Index: 581

Text #4

Max Range: 0.8828. Min Range: -0.8828

Max Act: 0.5926. Min Act: -0.0000

Data Index: 176545 (C4 (Web Text))

Max Activating Token Index: 460

Text #5

Max Range: 0.8828. Min Range: -0.8828

Max Act: 0.5572. Min Act: -0.0000

Data Index: 666693 (C4 (Web Text))

Max Activating Token Index: 558

Text #6

Max Range: 0.8828. Min Range: -0.8828

Max Act: 0.5111. Min Act: -0.0000

Data Index: 157044 (C4 (Web Text))

Max Activating Token Index: 120

Text #7

Max Range: 0.8828. Min Range: -0.8828

Max Act: 0.5101. Min Act: -0.0000

Data Index: 1309762 (C4 (Web Text))

Max Activating Token Index: 794

Text #8

Max Range: 0.8828. Min Range: -0.8828

Max Act: 0.4935. Min Act: -0.0000

Data Index: 1281058 (C4 (Web Text))

Max Activating Token Index: 348

Text #9

Max Range: 0.8828. Min Range: -0.8828

Max Act: 0.5042. Min Act: -0.0000

Data Index: 1308452 (C4 (Web Text))

Max Activating Token Index: 431

Text #10

Max Range: 0.8828. Min Range: -0.8828

Max Act: 0.4789. Min Act: -0.0000

Data Index: 66008 (C4 (Web Text))

Max Activating Token Index: 146

Text #11

Max Range: 0.8828. Min Range: -0.8828

Max Act: 0.4778. Min Act: -0.0000

Data Index: 1249412 (C4 (Web Text))

Max Activating Token Index: 449

Text #12

Max Range: 0.8828. Min Range: -0.8828

Max Act: 0.5474. Min Act: -0.0000

Data Index: 993418 (C4 (Web Text))

Max Activating Token Index: 176

Text #13

Max Range: 0.8828. Min Range: -0.8828

Max Act: 0.5004. Min Act: -0.0000

Data Index: 1221321 (C4 (Web Text))

Max Activating Token Index: 127

Text #14

Max Range: 0.8828. Min Range: -0.8828

Max Act: 0.5093. Min Act: -0.0000

Data Index: 743975 (C4 (Web Text))

Max Activating Token Index: 286

Text #15

Max Range: 0.8828. Min Range: -0.8828

Max Act: 0.5156. Min Act: -0.0000

Data Index: 420851 (C4 (Web Text))

Max Activating Token Index: 354

Text #16

Max Range: 0.8828. Min Range: -0.8828

Max Act: 0.5151. Min Act: -0.0000

Data Index: 459025 (C4 (Web Text))

Max Activating Token Index: 383

Text #17

Max Range: 0.8828. Min Range: -0.8828

Max Act: 0.4447. Min Act: -0.0000

Data Index: 1076814 (C4 (Web Text))

Max Activating Token Index: 667

Text #18

Max Range: 0.8828. Min Range: -0.8828

Max Act: 0.4901. Min Act: -0.0000

Data Index: 928065 (C4 (Web Text))

Max Activating Token Index: 392

Text #19

Max Range: 0.8828. Min Range: -0.8828

Max Act: 0.4567. Min Act: -0.0000

Data Index: 191486 (C4 (Web Text))

Max Activating Token Index: 773