Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4301 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.9030. Min Range: -1.9030

Max Act: 1.8605. Min Act: -0.0001

Data Index: 1154410 (C4 (Web Text))

Max Activating Token Index: 34

Text #1

Max Range: 1.9030. Min Range: -1.9030

Max Act: 1.9030. Min Act: -0.0001

Data Index: 1157767 (C4 (Web Text))

Max Activating Token Index: 215

Text #2

Max Range: 1.9030. Min Range: -1.9030

Max Act: 1.8798. Min Act: -0.0001

Data Index: 135620 (C4 (Web Text))

Max Activating Token Index: 576

Text #3

Max Range: 1.9030. Min Range: -1.9030

Max Act: 1.4554. Min Act: -0.0001

Data Index: 1082260 (C4 (Web Text))

Max Activating Token Index: 615

Text #4

Max Range: 1.9030. Min Range: -1.9030

Max Act: 1.6035. Min Act: -0.0001

Data Index: 815021 (C4 (Web Text))

Max Activating Token Index: 485

Text #5

Max Range: 1.9030. Min Range: -1.9030

Max Act: 1.5851. Min Act: -0.0001

Data Index: 1123078 (C4 (Web Text))

Max Activating Token Index: 711

Text #6

Max Range: 1.9030. Min Range: -1.9030

Max Act: 1.5474. Min Act: -0.0001

Data Index: 757073 (C4 (Web Text))

Max Activating Token Index: 608

Text #7

Max Range: 1.9030. Min Range: -1.9030

Max Act: 1.4947. Min Act: -0.0001

Data Index: 1178008 (C4 (Web Text))

Max Activating Token Index: 888

Text #8

Max Range: 1.9030. Min Range: -1.9030

Max Act: 1.5618. Min Act: -0.0001

Data Index: 849997 (C4 (Web Text))

Max Activating Token Index: 82

Text #9

Max Range: 1.9030. Min Range: -1.9030

Max Act: 1.4489. Min Act: -0.0001

Data Index: 813426 (C4 (Web Text))

Max Activating Token Index: 363

Text #10

Max Range: 1.9030. Min Range: -1.9030

Max Act: 1.4217. Min Act: -0.0001

Data Index: 1169885 (C4 (Web Text))

Max Activating Token Index: 217

Text #11

Max Range: 1.9030. Min Range: -1.9030

Max Act: 1.6265. Min Act: -0.0001

Data Index: 622834 (C4 (Web Text))

Max Activating Token Index: 60

Text #12

Max Range: 1.9030. Min Range: -1.9030

Max Act: 1.4348. Min Act: -0.0001

Data Index: 481114 (C4 (Web Text))

Max Activating Token Index: 689

Text #13

Max Range: 1.9030. Min Range: -1.9030

Max Act: 1.3879. Min Act: -0.0001

Data Index: 466030 (C4 (Web Text))

Max Activating Token Index: 233

Text #14

Max Range: 1.9030. Min Range: -1.9030

Max Act: 1.5239. Min Act: -0.0001

Data Index: 847316 (C4 (Web Text))

Max Activating Token Index: 354

Text #15

Max Range: 1.9030. Min Range: -1.9030

Max Act: 1.4471. Min Act: -0.0001

Data Index: 5727 (C4 (Web Text))

Max Activating Token Index: 77

Text #16

Max Range: 1.9030. Min Range: -1.9030

Max Act: 1.5794. Min Act: -0.0001

Data Index: 1200075 (C4 (Web Text))

Max Activating Token Index: 367

Text #17

Max Range: 1.9030. Min Range: -1.9030

Max Act: 1.5383. Min Act: -0.0001

Data Index: 1019615 (C4 (Web Text))

Max Activating Token Index: 397

Text #18

Max Range: 1.9030. Min Range: -1.9030

Max Act: 1.4174. Min Act: -0.0001

Data Index: 278549 (C4 (Web Text))

Max Activating Token Index: 681

Text #19

Max Range: 1.9030. Min Range: -1.9030

Max Act: 1.6710. Min Act: -0.0001

Data Index: 47276 (C4 (Web Text))

Max Activating Token Index: 551