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

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

Neuron 4222 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8894. Min Range: -1.8894

Max Act: 1.8894. Min Act: -0.0000

Data Index: 964090 (C4 (Web Text))

Max Activating Token Index: 1005

Text #1

Max Range: 1.8894. Min Range: -1.8894

Max Act: 1.8124. Min Act: -0.0000

Data Index: 861955 (C4 (Web Text))

Max Activating Token Index: 708

Text #2

Max Range: 1.8894. Min Range: -1.8894

Max Act: 1.7020. Min Act: -0.0000

Data Index: 89448 (C4 (Web Text))

Max Activating Token Index: 842

Text #3

Max Range: 1.8894. Min Range: -1.8894

Max Act: 1.6622. Min Act: -0.0000

Data Index: 1262832 (C4 (Web Text))

Max Activating Token Index: 152

Text #4

Max Range: 1.8894. Min Range: -1.8894

Max Act: 1.6145. Min Act: -0.0000

Data Index: 179052 (C4 (Web Text))

Max Activating Token Index: 211

Text #5

Max Range: 1.8894. Min Range: -1.8894

Max Act: 1.5786. Min Act: -0.0000

Data Index: 362785 (C4 (Web Text))

Max Activating Token Index: 36

Text #6

Max Range: 1.8894. Min Range: -1.8894

Max Act: 1.4809. Min Act: -0.0000

Data Index: 253023 (C4 (Web Text))

Max Activating Token Index: 258

Text #7

Max Range: 1.8894. Min Range: -1.8894

Max Act: 1.4775. Min Act: -0.0000

Data Index: 642594 (C4 (Web Text))

Max Activating Token Index: 876

Text #8

Max Range: 1.8894. Min Range: -1.8894

Max Act: 1.5427. Min Act: -0.0000

Data Index: 915153 (C4 (Web Text))

Max Activating Token Index: 277

Text #9

Max Range: 1.8894. Min Range: -1.8894

Max Act: 1.6404. Min Act: -0.0000

Data Index: 826030 (C4 (Web Text))

Max Activating Token Index: 292

Text #10

Max Range: 1.8894. Min Range: -1.8894

Max Act: 1.5093. Min Act: -0.0000

Data Index: 32260 (C4 (Web Text))

Max Activating Token Index: 46

Text #11

Max Range: 1.8894. Min Range: -1.8894

Max Act: 1.4021. Min Act: -0.0000

Data Index: 590040 (C4 (Web Text))

Max Activating Token Index: 283

Text #12

Max Range: 1.8894. Min Range: -1.8894

Max Act: 1.5931. Min Act: -0.0000

Data Index: 475244 (C4 (Web Text))

Max Activating Token Index: 119

Text #13

Max Range: 1.8894. Min Range: -1.8894

Max Act: 1.4908. Min Act: -0.0000

Data Index: 105961 (C4 (Web Text))

Max Activating Token Index: 215

Text #14

Max Range: 1.8894. Min Range: -1.8894

Max Act: 1.4949. Min Act: -0.0000

Data Index: 212493 (C4 (Web Text))

Max Activating Token Index: 24

Text #15

Max Range: 1.8894. Min Range: -1.8894

Max Act: 1.3946. Min Act: -0.0000

Data Index: 125348 (C4 (Web Text))

Max Activating Token Index: 589

Text #16

Max Range: 1.8894. Min Range: -1.8894

Max Act: 1.4469. Min Act: -0.0000

Data Index: 871265 (C4 (Web Text))

Max Activating Token Index: 458

Text #17

Max Range: 1.8894. Min Range: -1.8894

Max Act: 1.3435. Min Act: -0.0000

Data Index: 388748 (C4 (Web Text))

Max Activating Token Index: 81

Text #18

Max Range: 1.8894. Min Range: -1.8894

Max Act: 1.4988. Min Act: -0.0000

Data Index: 579447 (C4 (Web Text))

Max Activating Token Index: 223

Text #19

Max Range: 1.8894. Min Range: -1.8894

Max Act: 1.4075. Min Act: -0.0000

Data Index: 918697 (C4 (Web Text))

Max Activating Token Index: 211