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

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

Neuron 5776 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8483. Min Range: -0.8483

Max Act: 0.8483. Min Act: -0.0000

Data Index: 150876 (C4 (Web Text))

Max Activating Token Index: 142

Text #1

Max Range: 0.8483. Min Range: -0.8483

Max Act: 0.7663. Min Act: -0.0000

Data Index: 609321 (C4 (Web Text))

Max Activating Token Index: 501

Text #2

Max Range: 0.8483. Min Range: -0.8483

Max Act: 0.8166. Min Act: -0.0000

Data Index: 1292391 (C4 (Web Text))

Max Activating Token Index: 803

Text #3

Max Range: 0.8483. Min Range: -0.8483

Max Act: 0.7767. Min Act: -0.0000

Data Index: 737730 (C4 (Web Text))

Max Activating Token Index: 346

Text #4

Max Range: 0.8483. Min Range: -0.8483

Max Act: 0.7938. Min Act: -0.0000

Data Index: 787525 (C4 (Web Text))

Max Activating Token Index: 516

Text #5

Max Range: 0.8483. Min Range: -0.8483

Max Act: 0.7489. Min Act: -0.0000

Data Index: 58946 (C4 (Web Text))

Max Activating Token Index: 689

Text #6

Max Range: 0.8483. Min Range: -0.8483

Max Act: 0.6923. Min Act: -0.0000

Data Index: 476193 (C4 (Web Text))

Max Activating Token Index: 405

Text #7

Max Range: 0.8483. Min Range: -0.8483

Max Act: 0.6211. Min Act: -0.0000

Data Index: 520015 (C4 (Web Text))

Max Activating Token Index: 181

Text #8

Max Range: 0.8483. Min Range: -0.8483

Max Act: 0.5504. Min Act: -0.0000

Data Index: 620441 (C4 (Web Text))

Max Activating Token Index: 763

Text #9

Max Range: 0.8483. Min Range: -0.8483

Max Act: 0.5636. Min Act: -0.0000

Data Index: 406115 (C4 (Web Text))

Max Activating Token Index: 562

Text #10

Max Range: 0.8483. Min Range: -0.8483

Max Act: 0.5943. Min Act: -0.0000

Data Index: 750535 (C4 (Web Text))

Max Activating Token Index: 804

Text #11

Max Range: 0.8483. Min Range: -0.8483

Max Act: 0.5924. Min Act: -0.0000

Data Index: 1126324 (C4 (Web Text))

Max Activating Token Index: 542

Text #12

Max Range: 0.8483. Min Range: -0.8483

Max Act: 0.5549. Min Act: -0.0000

Data Index: 278593 (C4 (Web Text))

Max Activating Token Index: 210

Text #13

Max Range: 0.8483. Min Range: -0.8483

Max Act: 0.5883. Min Act: -0.0000

Data Index: 892775 (C4 (Web Text))

Max Activating Token Index: 224

Text #14

Max Range: 0.8483. Min Range: -0.8483

Max Act: 0.5660. Min Act: -0.0000

Data Index: 853317 (C4 (Web Text))

Max Activating Token Index: 480

Text #15

Max Range: 0.8483. Min Range: -0.8483

Max Act: 0.5627. Min Act: -0.0000

Data Index: 604097 (C4 (Web Text))

Max Activating Token Index: 462

Text #16

Max Range: 0.8483. Min Range: -0.8483

Max Act: 0.5569. Min Act: -0.0000

Data Index: 137733 (C4 (Web Text))

Max Activating Token Index: 229

Text #17

Max Range: 0.8483. Min Range: -0.8483

Max Act: 0.5444. Min Act: -0.0000

Data Index: 144858 (C4 (Web Text))

Max Activating Token Index: 573

Text #18

Max Range: 0.8483. Min Range: -0.8483

Max Act: 0.5432. Min Act: -0.0000

Data Index: 47382 (C4 (Web Text))

Max Activating Token Index: 924

Text #19

Max Range: 0.8483. Min Range: -0.8483

Max Act: 0.5364. Min Act: -0.0000

Data Index: 630948 (C4 (Web Text))

Max Activating Token Index: 719