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

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

Neuron 1769 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7936. Min Range: -2.7936

Max Act: 2.7936. Min Act: -0.0000

Data Index: 831179 (C4 (Web Text))

Max Activating Token Index: 601

Text #1

Max Range: 2.7936. Min Range: -2.7936

Max Act: 2.3995. Min Act: -0.0000

Data Index: 631708 (C4 (Web Text))

Max Activating Token Index: 430

Text #2

Max Range: 2.7936. Min Range: -2.7936

Max Act: 2.3689. Min Act: -0.0000

Data Index: 740730 (C4 (Web Text))

Max Activating Token Index: 787

Text #3

Max Range: 2.7936. Min Range: -2.7936

Max Act: 2.2279. Min Act: -0.0000

Data Index: 994834 (C4 (Web Text))

Max Activating Token Index: 352

Text #4

Max Range: 2.7936. Min Range: -2.7936

Max Act: 2.4774. Min Act: -0.0000

Data Index: 1193053 (C4 (Web Text))

Max Activating Token Index: 400

Text #5

Max Range: 2.7936. Min Range: -2.7936

Max Act: 2.1704. Min Act: -0.0000

Data Index: 396363 (C4 (Web Text))

Max Activating Token Index: 500

Text #6

Max Range: 2.7936. Min Range: -2.7936

Max Act: 1.8621. Min Act: -0.0000

Data Index: 841925 (C4 (Web Text))

Max Activating Token Index: 1007

Text #7

Max Range: 2.7936. Min Range: -2.7936

Max Act: 2.3232. Min Act: -0.0000

Data Index: 778146 (C4 (Web Text))

Max Activating Token Index: 890

Text #8

Max Range: 2.7936. Min Range: -2.7936

Max Act: 1.9430. Min Act: -0.0000

Data Index: 633245 (C4 (Web Text))

Max Activating Token Index: 331

Text #9

Max Range: 2.7936. Min Range: -2.7936

Max Act: 1.9286. Min Act: -0.0000

Data Index: 371475 (C4 (Web Text))

Max Activating Token Index: 852

Text #10

Max Range: 2.7936. Min Range: -2.7936

Max Act: 1.8759. Min Act: -0.0000

Data Index: 176721 (C4 (Web Text))

Max Activating Token Index: 411

Text #11

Max Range: 2.7936. Min Range: -2.7936

Max Act: 2.0594. Min Act: -0.0000

Data Index: 599716 (C4 (Web Text))

Max Activating Token Index: 743

Text #12

Max Range: 2.7936. Min Range: -2.7936

Max Act: 1.9220. Min Act: -0.0000

Data Index: 357108 (C4 (Web Text))

Max Activating Token Index: 295

Text #13

Max Range: 2.7936. Min Range: -2.7936

Max Act: 1.8104. Min Act: -0.0000

Data Index: 974643 (C4 (Web Text))

Max Activating Token Index: 169

Text #14

Max Range: 2.7936. Min Range: -2.7936

Max Act: 1.9051. Min Act: -0.0000

Data Index: 827069 (C4 (Web Text))

Max Activating Token Index: 239

Text #15

Max Range: 2.7936. Min Range: -2.7936

Max Act: 2.0005. Min Act: -0.0000

Data Index: 1261091 (C4 (Web Text))

Max Activating Token Index: 532

Text #16

Max Range: 2.7936. Min Range: -2.7936

Max Act: 1.7814. Min Act: -0.0000

Data Index: 768912 (C4 (Web Text))

Max Activating Token Index: 910

Text #17

Max Range: 2.7936. Min Range: -2.7936

Max Act: 1.7359. Min Act: -0.0000

Data Index: 704592 (C4 (Web Text))

Max Activating Token Index: 291

Text #18

Max Range: 2.7936. Min Range: -2.7936

Max Act: 1.8316. Min Act: -0.0000

Data Index: 676884 (C4 (Web Text))

Max Activating Token Index: 92

Text #19

Max Range: 2.7936. Min Range: -2.7936

Max Act: 1.8316. Min Act: -0.0000

Data Index: 485538 (C4 (Web Text))

Max Activating Token Index: 224