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

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

Neuron 5046 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4819. Min Range: -1.4819

Max Act: 1.3128. Min Act: -0.0001

Data Index: 183665 (C4 (Web Text))

Max Activating Token Index: 293

Text #1

Max Range: 1.4819. Min Range: -1.4819

Max Act: 1.2619. Min Act: -0.0001

Data Index: 1505040 (Python Code)

Max Activating Token Index: 469

Text #2

Max Range: 1.4819. Min Range: -1.4819

Max Act: 1.4819. Min Act: -0.0001

Data Index: 303608 (C4 (Web Text))

Max Activating Token Index: 805

Text #3

Max Range: 1.4819. Min Range: -1.4819

Max Act: 1.2869. Min Act: -0.0001

Data Index: 1027881 (C4 (Web Text))

Max Activating Token Index: 106

Text #4

Max Range: 1.4819. Min Range: -1.4819

Max Act: 1.1968. Min Act: -0.0001

Data Index: 628146 (C4 (Web Text))

Max Activating Token Index: 676

Text #5

Max Range: 1.4819. Min Range: -1.4819

Max Act: 1.1573. Min Act: -0.0001

Data Index: 1406518 (Python Code)

Max Activating Token Index: 35

Text #6

Max Range: 1.4819. Min Range: -1.4819

Max Act: 1.2486. Min Act: -0.0001

Data Index: 1367656 (Python Code)

Max Activating Token Index: 516

Text #7

Max Range: 1.4819. Min Range: -1.4819

Max Act: 1.1862. Min Act: -0.0001

Data Index: 1595781 (Python Code)

Max Activating Token Index: 192

Text #8

Max Range: 1.4819. Min Range: -1.4819

Max Act: 1.3038. Min Act: -0.0001

Data Index: 1607912 (Python Code)

Max Activating Token Index: 354

Text #9

Max Range: 1.4819. Min Range: -1.4819

Max Act: 0.9985. Min Act: -0.0001

Data Index: 1029870 (C4 (Web Text))

Max Activating Token Index: 270

Text #10

Max Range: 1.4819. Min Range: -1.4819

Max Act: 1.2821. Min Act: -0.0001

Data Index: 1364903 (Python Code)

Max Activating Token Index: 92

Text #11

Max Range: 1.4819. Min Range: -1.4819

Max Act: 1.2104. Min Act: -0.0001

Data Index: 1554087 (Python Code)

Max Activating Token Index: 358

Text #12

Max Range: 1.4819. Min Range: -1.4819

Max Act: 1.0964. Min Act: -0.0001

Data Index: 1363491 (Python Code)

Max Activating Token Index: 119

Text #13

Max Range: 1.4819. Min Range: -1.4819

Max Act: 1.1892. Min Act: -0.0001

Data Index: 1612740 (Python Code)

Max Activating Token Index: 152

Text #14

Max Range: 1.4819. Min Range: -1.4819

Max Act: 1.1537. Min Act: -0.0001

Data Index: 516807 (C4 (Web Text))

Max Activating Token Index: 674

Text #15

Max Range: 1.4819. Min Range: -1.4819

Max Act: 1.1572. Min Act: -0.0001

Data Index: 1560266 (Python Code)

Max Activating Token Index: 573

Text #16

Max Range: 1.4819. Min Range: -1.4819

Max Act: 1.1163. Min Act: -0.0001

Data Index: 1596887 (Python Code)

Max Activating Token Index: 720

Text #17

Max Range: 1.4819. Min Range: -1.4819

Max Act: 1.0983. Min Act: -0.0001

Data Index: 1503189 (Python Code)

Max Activating Token Index: 776

Text #18

Max Range: 1.4819. Min Range: -1.4819

Max Act: 1.0030. Min Act: -0.0001

Data Index: 1140733 (C4 (Web Text))

Max Activating Token Index: 185

Text #19

Max Range: 1.4819. Min Range: -1.4819

Max Act: 0.9875. Min Act: -0.0001

Data Index: 564486 (C4 (Web Text))

Max Activating Token Index: 337