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

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

Neuron 246 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3094. Min Range: -1.3094

Max Act: 1.3094. Min Act: -0.0000

Data Index: 986234 (C4 (Web Text))

Max Activating Token Index: 323

Text #1

Max Range: 1.3094. Min Range: -1.3094

Max Act: 1.2711. Min Act: -0.0000

Data Index: 1207005 (C4 (Web Text))

Max Activating Token Index: 325

Text #2

Max Range: 1.3094. Min Range: -1.3094

Max Act: 1.0196. Min Act: -0.0000

Data Index: 1357951 (C4 (Web Text))

Max Activating Token Index: 127

Text #3

Max Range: 1.3094. Min Range: -1.3094

Max Act: 1.1008. Min Act: -0.0000

Data Index: 997518 (C4 (Web Text))

Max Activating Token Index: 302

Text #4

Max Range: 1.3094. Min Range: -1.3094

Max Act: 1.0165. Min Act: -0.0000

Data Index: 1002702 (C4 (Web Text))

Max Activating Token Index: 748

Text #5

Max Range: 1.3094. Min Range: -1.3094

Max Act: 0.9395. Min Act: -0.0000

Data Index: 772885 (C4 (Web Text))

Max Activating Token Index: 155

Text #6

Max Range: 1.3094. Min Range: -1.3094

Max Act: 1.0463. Min Act: -0.0000

Data Index: 1294088 (C4 (Web Text))

Max Activating Token Index: 787

Text #7

Max Range: 1.3094. Min Range: -1.3094

Max Act: 0.9520. Min Act: -0.0000

Data Index: 402592 (C4 (Web Text))

Max Activating Token Index: 410

Text #8

Max Range: 1.3094. Min Range: -1.3094

Max Act: 0.8817. Min Act: -0.0000

Data Index: 429442 (C4 (Web Text))

Max Activating Token Index: 866

Text #9

Max Range: 1.3094. Min Range: -1.3094

Max Act: 0.8947. Min Act: -0.0000

Data Index: 103219 (C4 (Web Text))

Max Activating Token Index: 342

Text #10

Max Range: 1.3094. Min Range: -1.3094

Max Act: 0.9475. Min Act: -0.0000

Data Index: 1285007 (C4 (Web Text))

Max Activating Token Index: 732

Text #11

Max Range: 1.3094. Min Range: -1.3094

Max Act: 0.8742. Min Act: -0.0000

Data Index: 821897 (C4 (Web Text))

Max Activating Token Index: 1007

Text #12

Max Range: 1.3094. Min Range: -1.3094

Max Act: 0.7944. Min Act: -0.0000

Data Index: 74842 (C4 (Web Text))

Max Activating Token Index: 239

Text #13

Max Range: 1.3094. Min Range: -1.3094

Max Act: 0.8875. Min Act: -0.0000

Data Index: 1258487 (C4 (Web Text))

Max Activating Token Index: 180

Text #14

Max Range: 1.3094. Min Range: -1.3094

Max Act: 0.8634. Min Act: -0.0000

Data Index: 488807 (C4 (Web Text))

Max Activating Token Index: 400

Text #15

Max Range: 1.3094. Min Range: -1.3094

Max Act: 0.8710. Min Act: -0.0000

Data Index: 69594 (C4 (Web Text))

Max Activating Token Index: 709

Text #16

Max Range: 1.3094. Min Range: -1.3094

Max Act: 0.7540. Min Act: -0.0000

Data Index: 883747 (C4 (Web Text))

Max Activating Token Index: 722

Text #17

Max Range: 1.3094. Min Range: -1.3094

Max Act: 0.6910. Min Act: -0.0000

Data Index: 438360 (C4 (Web Text))

Max Activating Token Index: 752

Text #18

Max Range: 1.3094. Min Range: -1.3094

Max Act: 0.7595. Min Act: -0.0000

Data Index: 166844 (C4 (Web Text))

Max Activating Token Index: 272

Text #19

Max Range: 1.3094. Min Range: -1.3094

Max Act: 0.7317. Min Act: -0.0000

Data Index: 163758 (C4 (Web Text))

Max Activating Token Index: 784