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

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

Neuron 2251 in Layer 0

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: 0.6827. Min Range: -0.6827

Max Act: 0.6827. Min Act: -0.0001

Data Index: 734712 (C4 (Web Text))

Max Activating Token Index: 990

Text #1

Max Range: 0.6827. Min Range: -0.6827

Max Act: 0.6759. Min Act: -0.0001

Data Index: 347168 (C4 (Web Text))

Max Activating Token Index: 392

Text #2

Max Range: 0.6827. Min Range: -0.6827

Max Act: 0.6672. Min Act: -0.0001

Data Index: 1087329 (C4 (Web Text))

Max Activating Token Index: 131

Text #3

Max Range: 0.6827. Min Range: -0.6827

Max Act: 0.6737. Min Act: -0.0001

Data Index: 1266983 (C4 (Web Text))

Max Activating Token Index: 560

Text #4

Max Range: 0.6827. Min Range: -0.6827

Max Act: 0.6605. Min Act: -0.0001

Data Index: 1221763 (C4 (Web Text))

Max Activating Token Index: 333

Text #5

Max Range: 0.6827. Min Range: -0.6827

Max Act: 0.6742. Min Act: -0.0001

Data Index: 308278 (C4 (Web Text))

Max Activating Token Index: 163

Text #6

Max Range: 0.6827. Min Range: -0.6827

Max Act: 0.6591. Min Act: -0.0001

Data Index: 427179 (C4 (Web Text))

Max Activating Token Index: 382

Text #7

Max Range: 0.6827. Min Range: -0.6827

Max Act: 0.6553. Min Act: -0.0001

Data Index: 195339 (C4 (Web Text))

Max Activating Token Index: 334

Text #8

Max Range: 0.6827. Min Range: -0.6827

Max Act: 0.6424. Min Act: -0.0001

Data Index: 1298994 (C4 (Web Text))

Max Activating Token Index: 128

Text #9

Max Range: 0.6827. Min Range: -0.6827

Max Act: 0.6495. Min Act: -0.0001

Data Index: 149811 (C4 (Web Text))

Max Activating Token Index: 165

Text #10

Max Range: 0.6827. Min Range: -0.6827

Max Act: 0.6372. Min Act: -0.0001

Data Index: 764474 (C4 (Web Text))

Max Activating Token Index: 123

Text #11

Max Range: 0.6827. Min Range: -0.6827

Max Act: 0.6306. Min Act: -0.0001

Data Index: 565429 (C4 (Web Text))

Max Activating Token Index: 704

Text #12

Max Range: 0.6827. Min Range: -0.6827

Max Act: 0.6415. Min Act: -0.0002

Data Index: 10964 (C4 (Web Text))

Max Activating Token Index: 243

Text #13

Max Range: 0.6827. Min Range: -0.6827

Max Act: 0.6241. Min Act: -0.0001

Data Index: 573065 (C4 (Web Text))

Max Activating Token Index: 948

Text #14

Max Range: 0.6827. Min Range: -0.6827

Max Act: 0.6295. Min Act: -0.0001

Data Index: 808658 (C4 (Web Text))

Max Activating Token Index: 97

Text #15

Max Range: 0.6827. Min Range: -0.6827

Max Act: 0.6124. Min Act: -0.0001

Data Index: 264861 (C4 (Web Text))

Max Activating Token Index: 853

Text #16

Max Range: 0.6827. Min Range: -0.6827

Max Act: 0.6187. Min Act: -0.0001

Data Index: 100630 (C4 (Web Text))

Max Activating Token Index: 502

Text #17

Max Range: 0.6827. Min Range: -0.6827

Max Act: 0.6286. Min Act: -0.0001

Data Index: 807145 (C4 (Web Text))

Max Activating Token Index: 382

Text #18

Max Range: 0.6827. Min Range: -0.6827

Max Act: 0.6147. Min Act: -0.0001

Data Index: 886447 (C4 (Web Text))

Max Activating Token Index: 756

Text #19

Max Range: 0.6827. Min Range: -0.6827

Max Act: 0.6280. Min Act: -0.0001

Data Index: 146159 (C4 (Web Text))

Max Activating Token Index: 26