Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4840 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.8810. Min Range: -1.8810

Max Act: 1.8810. Min Act: -0.0000

Data Index: 914080 (C4 (Web Text))

Max Activating Token Index: 277

Text #1

Max Range: 1.8810. Min Range: -1.8810

Max Act: 1.8269. Min Act: -0.0000

Data Index: 162312 (C4 (Web Text))

Max Activating Token Index: 425

Text #2

Max Range: 1.8810. Min Range: -1.8810

Max Act: 1.8091. Min Act: -0.0000

Data Index: 355432 (C4 (Web Text))

Max Activating Token Index: 484

Text #3

Max Range: 1.8810. Min Range: -1.8810

Max Act: 1.6465. Min Act: -0.0000

Data Index: 618310 (C4 (Web Text))

Max Activating Token Index: 319

Text #4

Max Range: 1.8810. Min Range: -1.8810

Max Act: 1.6319. Min Act: -0.0000

Data Index: 313320 (C4 (Web Text))

Max Activating Token Index: 981

Text #5

Max Range: 1.8810. Min Range: -1.8810

Max Act: 1.6165. Min Act: -0.0000

Data Index: 101618 (C4 (Web Text))

Max Activating Token Index: 49

Text #6

Max Range: 1.8810. Min Range: -1.8810

Max Act: 1.6160. Min Act: -0.0000

Data Index: 361149 (C4 (Web Text))

Max Activating Token Index: 624

Text #7

Max Range: 1.8810. Min Range: -1.8810

Max Act: 1.5787. Min Act: -0.0000

Data Index: 685454 (C4 (Web Text))

Max Activating Token Index: 236

Text #8

Max Range: 1.8810. Min Range: -1.8810

Max Act: 1.5603. Min Act: -0.0000

Data Index: 688828 (C4 (Web Text))

Max Activating Token Index: 187

Text #9

Max Range: 1.8810. Min Range: -1.8810

Max Act: 1.4604. Min Act: -0.0000

Data Index: 87631 (C4 (Web Text))

Max Activating Token Index: 770

Text #10

Max Range: 1.8810. Min Range: -1.8810

Max Act: 1.5150. Min Act: -0.0000

Data Index: 530187 (C4 (Web Text))

Max Activating Token Index: 772

Text #11

Max Range: 1.8810. Min Range: -1.8810

Max Act: 1.5079. Min Act: -0.0000

Data Index: 987270 (C4 (Web Text))

Max Activating Token Index: 193

Text #12

Max Range: 1.8810. Min Range: -1.8810

Max Act: 1.4928. Min Act: -0.0000

Data Index: 951967 (C4 (Web Text))

Max Activating Token Index: 671

Text #13

Max Range: 1.8810. Min Range: -1.8810

Max Act: 1.5819. Min Act: -0.0000

Data Index: 182728 (C4 (Web Text))

Max Activating Token Index: 677

Text #14

Max Range: 1.8810. Min Range: -1.8810

Max Act: 1.5663. Min Act: -0.0000

Data Index: 761923 (C4 (Web Text))

Max Activating Token Index: 268

Text #15

Max Range: 1.8810. Min Range: -1.8810

Max Act: 1.4825. Min Act: -0.0000

Data Index: 563844 (C4 (Web Text))

Max Activating Token Index: 730

Text #16

Max Range: 1.8810. Min Range: -1.8810

Max Act: 1.4801. Min Act: -0.0000

Data Index: 480826 (C4 (Web Text))

Max Activating Token Index: 22

Text #17

Max Range: 1.8810. Min Range: -1.8810

Max Act: 1.5660. Min Act: -0.0000

Data Index: 308894 (C4 (Web Text))

Max Activating Token Index: 870

Text #18

Max Range: 1.8810. Min Range: -1.8810

Max Act: 1.5615. Min Act: -0.0000

Data Index: 1227404 (C4 (Web Text))

Max Activating Token Index: 81

Text #19

Max Range: 1.8810. Min Range: -1.8810

Max Act: 1.4283. Min Act: -0.0000

Data Index: 540874 (C4 (Web Text))

Max Activating Token Index: 538