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

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

Neuron 4848 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8089. Min Range: -0.8089

Max Act: 0.8089. Min Act: -0.0001

Data Index: 816663 (C4 (Web Text))

Max Activating Token Index: 269

Text #1

Max Range: 0.8089. Min Range: -0.8089

Max Act: 0.6865. Min Act: -0.0001

Data Index: 131019 (C4 (Web Text))

Max Activating Token Index: 255

Text #2

Max Range: 0.8089. Min Range: -0.8089

Max Act: 0.6698. Min Act: -0.0001

Data Index: 1111801 (C4 (Web Text))

Max Activating Token Index: 527

Text #3

Max Range: 0.8089. Min Range: -0.8089

Max Act: 0.5824. Min Act: -0.0001

Data Index: 1090417 (C4 (Web Text))

Max Activating Token Index: 358

Text #4

Max Range: 0.8089. Min Range: -0.8089

Max Act: 0.5960. Min Act: -0.0001

Data Index: 924287 (C4 (Web Text))

Max Activating Token Index: 873

Text #5

Max Range: 0.8089. Min Range: -0.8089

Max Act: 0.5975. Min Act: -0.0001

Data Index: 1143274 (C4 (Web Text))

Max Activating Token Index: 663

Text #6

Max Range: 0.8089. Min Range: -0.8089

Max Act: 0.5942. Min Act: -0.0001

Data Index: 710910 (C4 (Web Text))

Max Activating Token Index: 466

Text #7

Max Range: 0.8089. Min Range: -0.8089

Max Act: 0.5691. Min Act: -0.0001

Data Index: 327484 (C4 (Web Text))

Max Activating Token Index: 241

Text #8

Max Range: 0.8089. Min Range: -0.8089

Max Act: 0.5781. Min Act: -0.0001

Data Index: 1297668 (C4 (Web Text))

Max Activating Token Index: 52

Text #9

Max Range: 0.8089. Min Range: -0.8089

Max Act: 0.5461. Min Act: -0.0001

Data Index: 202538 (C4 (Web Text))

Max Activating Token Index: 827

Text #10

Max Range: 0.8089. Min Range: -0.8089

Max Act: 0.5799. Min Act: -0.0001

Data Index: 915690 (C4 (Web Text))

Max Activating Token Index: 699

Text #11

Max Range: 0.8089. Min Range: -0.8089

Max Act: 0.5395. Min Act: -0.0001

Data Index: 694679 (C4 (Web Text))

Max Activating Token Index: 1005

Text #12

Max Range: 0.8089. Min Range: -0.8089

Max Act: 0.5471. Min Act: -0.0001

Data Index: 1319708 (C4 (Web Text))

Max Activating Token Index: 182

Text #13

Max Range: 0.8089. Min Range: -0.8089

Max Act: 0.6173. Min Act: -0.0001

Data Index: 62868 (C4 (Web Text))

Max Activating Token Index: 323

Text #14

Max Range: 0.8089. Min Range: -0.8089

Max Act: 0.5283. Min Act: -0.0001

Data Index: 1250476 (C4 (Web Text))

Max Activating Token Index: 560

Text #15

Max Range: 0.8089. Min Range: -0.8089

Max Act: 0.5558. Min Act: -0.0001

Data Index: 541618 (C4 (Web Text))

Max Activating Token Index: 909

Text #16

Max Range: 0.8089. Min Range: -0.8089

Max Act: 0.5507. Min Act: -0.0001

Data Index: 258273 (C4 (Web Text))

Max Activating Token Index: 199

Text #17

Max Range: 0.8089. Min Range: -0.8089

Max Act: 0.4963. Min Act: -0.0001

Data Index: 597201 (C4 (Web Text))

Max Activating Token Index: 190

Text #18

Max Range: 0.8089. Min Range: -0.8089

Max Act: 0.4876. Min Act: -0.0001

Data Index: 148087 (C4 (Web Text))

Max Activating Token Index: 181

Text #19

Max Range: 0.8089. Min Range: -0.8089

Max Act: 0.5286. Min Act: -0.0001

Data Index: 63055 (C4 (Web Text))

Max Activating Token Index: 240