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

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

Neuron 4096 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 2.6821. Min Range: -2.6821

Max Act: 2.6821. Min Act: -0.0002

Data Index: 1300051 (C4 (Web Text))

Max Activating Token Index: 103

Text #1

Max Range: 2.6821. Min Range: -2.6821

Max Act: 2.3653. Min Act: -0.0002

Data Index: 80422 (C4 (Web Text))

Max Activating Token Index: 246

Text #2

Max Range: 2.6821. Min Range: -2.6821

Max Act: 2.2378. Min Act: -0.0002

Data Index: 22482 (C4 (Web Text))

Max Activating Token Index: 288

Text #3

Max Range: 2.6821. Min Range: -2.6821

Max Act: 2.1285. Min Act: -0.0002

Data Index: 1002205 (C4 (Web Text))

Max Activating Token Index: 298

Text #4

Max Range: 2.6821. Min Range: -2.6821

Max Act: 2.1125. Min Act: -0.0002

Data Index: 672719 (C4 (Web Text))

Max Activating Token Index: 368

Text #5

Max Range: 2.6821. Min Range: -2.6821

Max Act: 2.1320. Min Act: -0.0002

Data Index: 353149 (C4 (Web Text))

Max Activating Token Index: 141

Text #6

Max Range: 2.6821. Min Range: -2.6821

Max Act: 2.1305. Min Act: -0.0002

Data Index: 14607 (C4 (Web Text))

Max Activating Token Index: 168

Text #7

Max Range: 2.6821. Min Range: -2.6821

Max Act: 2.0625. Min Act: -0.0003

Data Index: 1337866 (C4 (Web Text))

Max Activating Token Index: 144

Text #8

Max Range: 2.6821. Min Range: -2.6821

Max Act: 2.0404. Min Act: -0.0002

Data Index: 425177 (C4 (Web Text))

Max Activating Token Index: 82

Text #9

Max Range: 2.6821. Min Range: -2.6821

Max Act: 2.0101. Min Act: -0.0002

Data Index: 840555 (C4 (Web Text))

Max Activating Token Index: 177

Text #10

Max Range: 2.6821. Min Range: -2.6821

Max Act: 1.9803. Min Act: -0.0002

Data Index: 310581 (C4 (Web Text))

Max Activating Token Index: 164

Text #11

Max Range: 2.6821. Min Range: -2.6821

Max Act: 1.9914. Min Act: -0.0003

Data Index: 646998 (C4 (Web Text))

Max Activating Token Index: 105

Text #12

Max Range: 2.6821. Min Range: -2.6821

Max Act: 1.9424. Min Act: -0.0002

Data Index: 748972 (C4 (Web Text))

Max Activating Token Index: 467

Text #13

Max Range: 2.6821. Min Range: -2.6821

Max Act: 1.9475. Min Act: -0.0002

Data Index: 1347679 (C4 (Web Text))

Max Activating Token Index: 272

Text #14

Max Range: 2.6821. Min Range: -2.6821

Max Act: 1.9185. Min Act: -0.0002

Data Index: 402917 (C4 (Web Text))

Max Activating Token Index: 509

Text #15

Max Range: 2.6821. Min Range: -2.6821

Max Act: 1.9248. Min Act: -0.0002

Data Index: 294355 (C4 (Web Text))

Max Activating Token Index: 281

Text #16

Max Range: 2.6821. Min Range: -2.6821

Max Act: 1.8750. Min Act: -0.0002

Data Index: 298131 (C4 (Web Text))

Max Activating Token Index: 182

Text #17

Max Range: 2.6821. Min Range: -2.6821

Max Act: 1.8723. Min Act: -0.0002

Data Index: 901270 (C4 (Web Text))

Max Activating Token Index: 694

Text #18

Max Range: 2.6821. Min Range: -2.6821

Max Act: 1.8880. Min Act: -0.0002

Data Index: 1123273 (C4 (Web Text))

Max Activating Token Index: 250

Text #19

Max Range: 2.6821. Min Range: -2.6821

Max Act: 1.8615. Min Act: -0.0002

Data Index: 808910 (C4 (Web Text))

Max Activating Token Index: 732