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

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

Neuron 3258 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9730. Min Range: -1.9730

Max Act: 1.9730. Min Act: -0.0001

Data Index: 648588 (C4 (Web Text))

Max Activating Token Index: 27

Text #1

Max Range: 1.9730. Min Range: -1.9730

Max Act: 1.7088. Min Act: -0.0001

Data Index: 1287299 (C4 (Web Text))

Max Activating Token Index: 958

Text #2

Max Range: 1.9730. Min Range: -1.9730

Max Act: 1.9535. Min Act: -0.0001

Data Index: 699387 (C4 (Web Text))

Max Activating Token Index: 178

Text #3

Max Range: 1.9730. Min Range: -1.9730

Max Act: 1.7617. Min Act: -0.0001

Data Index: 887074 (C4 (Web Text))

Max Activating Token Index: 439

Text #4

Max Range: 1.9730. Min Range: -1.9730

Max Act: 1.9711. Min Act: -0.0001

Data Index: 198637 (C4 (Web Text))

Max Activating Token Index: 216

Text #5

Max Range: 1.9730. Min Range: -1.9730

Max Act: 1.7445. Min Act: -0.0001

Data Index: 171113 (C4 (Web Text))

Max Activating Token Index: 692

Text #6

Max Range: 1.9730. Min Range: -1.9730

Max Act: 1.8161. Min Act: -0.0001

Data Index: 438416 (C4 (Web Text))

Max Activating Token Index: 322

Text #7

Max Range: 1.9730. Min Range: -1.9730

Max Act: 1.7605. Min Act: -0.0001

Data Index: 968731 (C4 (Web Text))

Max Activating Token Index: 318

Text #8

Max Range: 1.9730. Min Range: -1.9730

Max Act: 1.7097. Min Act: -0.0001

Data Index: 278193 (C4 (Web Text))

Max Activating Token Index: 265

Text #9

Max Range: 1.9730. Min Range: -1.9730

Max Act: 1.6607. Min Act: -0.0001

Data Index: 1110816 (C4 (Web Text))

Max Activating Token Index: 314

Text #10

Max Range: 1.9730. Min Range: -1.9730

Max Act: 1.5478. Min Act: -0.0001

Data Index: 1253940 (C4 (Web Text))

Max Activating Token Index: 152

Text #11

Max Range: 1.9730. Min Range: -1.9730

Max Act: 1.5971. Min Act: -0.0001

Data Index: 95148 (C4 (Web Text))

Max Activating Token Index: 121

Text #12

Max Range: 1.9730. Min Range: -1.9730

Max Act: 1.6756. Min Act: -0.0001

Data Index: 411269 (C4 (Web Text))

Max Activating Token Index: 574

Text #13

Max Range: 1.9730. Min Range: -1.9730

Max Act: 1.4511. Min Act: -0.0001

Data Index: 1091867 (C4 (Web Text))

Max Activating Token Index: 844

Text #14

Max Range: 1.9730. Min Range: -1.9730

Max Act: 1.8012. Min Act: -0.0001

Data Index: 321333 (C4 (Web Text))

Max Activating Token Index: 907

Text #15

Max Range: 1.9730. Min Range: -1.9730

Max Act: 1.8562. Min Act: -0.0001

Data Index: 802746 (C4 (Web Text))

Max Activating Token Index: 719

Text #16

Max Range: 1.9730. Min Range: -1.9730

Max Act: 1.3645. Min Act: -0.0001

Data Index: 589967 (C4 (Web Text))

Max Activating Token Index: 380

Text #17

Max Range: 1.9730. Min Range: -1.9730

Max Act: 1.5542. Min Act: -0.0001

Data Index: 740895 (C4 (Web Text))

Max Activating Token Index: 405

Text #18

Max Range: 1.9730. Min Range: -1.9730

Max Act: 1.6788. Min Act: -0.0001

Data Index: 1339835 (C4 (Web Text))

Max Activating Token Index: 33

Text #19

Max Range: 1.9730. Min Range: -1.9730

Max Act: 1.4498. Min Act: -0.0001

Data Index: 834288 (C4 (Web Text))

Max Activating Token Index: 208