Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2044 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 5.9805. Min Range: -5.9805

Max Act: 5.9805. Min Act: -0.0001

Data Index: 395646 (C4 (Web Text))

Max Activating Token Index: 683

Text #1

Max Range: 5.9805. Min Range: -5.9805

Max Act: 5.6338. Min Act: -0.0000

Data Index: 89697 (C4 (Web Text))

Max Activating Token Index: 335

Text #2

Max Range: 5.9805. Min Range: -5.9805

Max Act: 5.3850. Min Act: -0.0001

Data Index: 500909 (C4 (Web Text))

Max Activating Token Index: 1017

Text #3

Max Range: 5.9805. Min Range: -5.9805

Max Act: 5.1570. Min Act: -0.0001

Data Index: 4792 (C4 (Web Text))

Max Activating Token Index: 198

Text #4

Max Range: 5.9805. Min Range: -5.9805

Max Act: 5.0994. Min Act: -0.0001

Data Index: 821133 (C4 (Web Text))

Max Activating Token Index: 931

Text #5

Max Range: 5.9805. Min Range: -5.9805

Max Act: 5.2383. Min Act: -0.0001

Data Index: 279064 (C4 (Web Text))

Max Activating Token Index: 268

Text #6

Max Range: 5.9805. Min Range: -5.9805

Max Act: 4.9224. Min Act: -0.0001

Data Index: 186276 (C4 (Web Text))

Max Activating Token Index: 566

Text #7

Max Range: 5.9805. Min Range: -5.9805

Max Act: 4.9642. Min Act: -0.0001

Data Index: 476857 (C4 (Web Text))

Max Activating Token Index: 297

Text #8

Max Range: 5.9805. Min Range: -5.9805

Max Act: 4.4117. Min Act: -0.0001

Data Index: 1027844 (C4 (Web Text))

Max Activating Token Index: 837

Text #9

Max Range: 5.9805. Min Range: -5.9805

Max Act: 4.6405. Min Act: -0.0001

Data Index: 49597 (C4 (Web Text))

Max Activating Token Index: 802

Text #10

Max Range: 5.9805. Min Range: -5.9805

Max Act: 4.3890. Min Act: -0.0001

Data Index: 398839 (C4 (Web Text))

Max Activating Token Index: 516

Text #11

Max Range: 5.9805. Min Range: -5.9805

Max Act: 4.5583. Min Act: -0.0001

Data Index: 753804 (C4 (Web Text))

Max Activating Token Index: 609

Text #12

Max Range: 5.9805. Min Range: -5.9805

Max Act: 4.8620. Min Act: -0.0001

Data Index: 119299 (C4 (Web Text))

Max Activating Token Index: 383

Text #13

Max Range: 5.9805. Min Range: -5.9805

Max Act: 4.3408. Min Act: -0.0001

Data Index: 896899 (C4 (Web Text))

Max Activating Token Index: 1004

Text #14

Max Range: 5.9805. Min Range: -5.9805

Max Act: 4.5145. Min Act: -0.0001

Data Index: 221964 (C4 (Web Text))

Max Activating Token Index: 283

Text #15

Max Range: 5.9805. Min Range: -5.9805

Max Act: 4.3689. Min Act: -0.0001

Data Index: 905128 (C4 (Web Text))

Max Activating Token Index: 895

Text #16

Max Range: 5.9805. Min Range: -5.9805

Max Act: 4.6940. Min Act: -0.0001

Data Index: 1071625 (C4 (Web Text))

Max Activating Token Index: 230

Text #17

Max Range: 5.9805. Min Range: -5.9805

Max Act: 4.3039. Min Act: -0.0001

Data Index: 754769 (C4 (Web Text))

Max Activating Token Index: 97

Text #18

Max Range: 5.9805. Min Range: -5.9805

Max Act: 4.4597. Min Act: -0.0001

Data Index: 1232889 (C4 (Web Text))

Max Activating Token Index: 821

Text #19

Max Range: 5.9805. Min Range: -5.9805

Max Act: 4.4591. Min Act: -0.0001

Data Index: 675176 (C4 (Web Text))

Max Activating Token Index: 908