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

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

Neuron 3823 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8661. Min Range: -1.8661

Max Act: 1.8456. Min Act: -0.0001

Data Index: 1496484 (Python Code)

Max Activating Token Index: 17

Text #1

Max Range: 1.8661. Min Range: -1.8661

Max Act: 1.7739. Min Act: -0.0001

Data Index: 1373730 (Python Code)

Max Activating Token Index: 650

Text #2

Max Range: 1.8661. Min Range: -1.8661

Max Act: 1.8661. Min Act: -0.0001

Data Index: 1562201 (Python Code)

Max Activating Token Index: 14

Text #3

Max Range: 1.8661. Min Range: -1.8661

Max Act: 1.4471. Min Act: -0.0001

Data Index: 1491872 (Python Code)

Max Activating Token Index: 229

Text #4

Max Range: 1.8661. Min Range: -1.8661

Max Act: 1.4806. Min Act: -0.0001

Data Index: 1581021 (Python Code)

Max Activating Token Index: 173

Text #5

Max Range: 1.8661. Min Range: -1.8661

Max Act: 1.5991. Min Act: -0.0001

Data Index: 1366938 (Python Code)

Max Activating Token Index: 259

Text #6

Max Range: 1.8661. Min Range: -1.8661

Max Act: 1.4851. Min Act: -0.0001

Data Index: 1385387 (Python Code)

Max Activating Token Index: 108

Text #7

Max Range: 1.8661. Min Range: -1.8661

Max Act: 1.5727. Min Act: -0.0001

Data Index: 1532186 (Python Code)

Max Activating Token Index: 163

Text #8

Max Range: 1.8661. Min Range: -1.8661

Max Act: 1.5640. Min Act: -0.0001

Data Index: 1607012 (Python Code)

Max Activating Token Index: 197

Text #9

Max Range: 1.8661. Min Range: -1.8661

Max Act: 1.5237. Min Act: -0.0001

Data Index: 1636764 (Python Code)

Max Activating Token Index: 70

Text #10

Max Range: 1.8661. Min Range: -1.8661

Max Act: 1.4783. Min Act: -0.0001

Data Index: 1536653 (Python Code)

Max Activating Token Index: 216

Text #11

Max Range: 1.8661. Min Range: -1.8661

Max Act: 1.4618. Min Act: -0.0001

Data Index: 1510642 (Python Code)

Max Activating Token Index: 443

Text #12

Max Range: 1.8661. Min Range: -1.8661

Max Act: 1.4564. Min Act: -0.0001

Data Index: 1494624 (Python Code)

Max Activating Token Index: 189

Text #13

Max Range: 1.8661. Min Range: -1.8661

Max Act: 1.4569. Min Act: -0.0001

Data Index: 1414913 (Python Code)

Max Activating Token Index: 746

Text #14

Max Range: 1.8661. Min Range: -1.8661

Max Act: 1.5277. Min Act: -0.0001

Data Index: 1516714 (Python Code)

Max Activating Token Index: 236

Text #15

Max Range: 1.8661. Min Range: -1.8661

Max Act: 1.4788. Min Act: -0.0001

Data Index: 1481162 (Python Code)

Max Activating Token Index: 183

Text #16

Max Range: 1.8661. Min Range: -1.8661

Max Act: 1.4801. Min Act: -0.0001

Data Index: 1570230 (Python Code)

Max Activating Token Index: 641

Text #17

Max Range: 1.8661. Min Range: -1.8661

Max Act: 1.4746. Min Act: -0.0001

Data Index: 1628344 (Python Code)

Max Activating Token Index: 826

Text #18

Max Range: 1.8661. Min Range: -1.8661

Max Act: 1.5147. Min Act: -0.0001

Data Index: 1565150 (Python Code)

Max Activating Token Index: 287

Text #19

Max Range: 1.8661. Min Range: -1.8661

Max Act: 1.4639. Min Act: -0.0001

Data Index: 1643062 (Python Code)

Max Activating Token Index: 773