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

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

Neuron 472 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7080. Min Range: -0.7080

Max Act: 0.6878. Min Act: -0.0001

Data Index: 819081 (C4 (Web Text))

Max Activating Token Index: 141

Text #1

Max Range: 0.7080. Min Range: -0.7080

Max Act: 0.6524. Min Act: -0.0001

Data Index: 63013 (C4 (Web Text))

Max Activating Token Index: 593

Text #2

Max Range: 0.7080. Min Range: -0.7080

Max Act: 0.7080. Min Act: -0.0000

Data Index: 1212071 (C4 (Web Text))

Max Activating Token Index: 61

Text #3

Max Range: 0.7080. Min Range: -0.7080

Max Act: 0.7038. Min Act: -0.0001

Data Index: 230884 (C4 (Web Text))

Max Activating Token Index: 447

Text #4

Max Range: 0.7080. Min Range: -0.7080

Max Act: 0.6103. Min Act: -0.0001

Data Index: 559389 (C4 (Web Text))

Max Activating Token Index: 121

Text #5

Max Range: 0.7080. Min Range: -0.7080

Max Act: 0.6294. Min Act: -0.0001

Data Index: 142778 (C4 (Web Text))

Max Activating Token Index: 211

Text #6

Max Range: 0.7080. Min Range: -0.7080

Max Act: 0.5968. Min Act: -0.0001

Data Index: 1217142 (C4 (Web Text))

Max Activating Token Index: 103

Text #7

Max Range: 0.7080. Min Range: -0.7080

Max Act: 0.5904. Min Act: -0.0000

Data Index: 32865 (C4 (Web Text))

Max Activating Token Index: 819

Text #8

Max Range: 0.7080. Min Range: -0.7080

Max Act: 0.6138. Min Act: -0.0001

Data Index: 1053034 (C4 (Web Text))

Max Activating Token Index: 418

Text #9

Max Range: 0.7080. Min Range: -0.7080

Max Act: 0.6345. Min Act: -0.0001

Data Index: 274592 (C4 (Web Text))

Max Activating Token Index: 509

Text #10

Max Range: 0.7080. Min Range: -0.7080

Max Act: 0.6686. Min Act: -0.0001

Data Index: 956253 (C4 (Web Text))

Max Activating Token Index: 300

Text #11

Max Range: 0.7080. Min Range: -0.7080

Max Act: 0.6363. Min Act: -0.0001

Data Index: 938371 (C4 (Web Text))

Max Activating Token Index: 854

Text #12

Max Range: 0.7080. Min Range: -0.7080

Max Act: 0.5797. Min Act: -0.0001

Data Index: 116780 (C4 (Web Text))

Max Activating Token Index: 228

Text #13

Max Range: 0.7080. Min Range: -0.7080

Max Act: 0.5729. Min Act: -0.0001

Data Index: 1079201 (C4 (Web Text))

Max Activating Token Index: 80

Text #14

Max Range: 0.7080. Min Range: -0.7080

Max Act: 0.6231. Min Act: -0.0001

Data Index: 1202649 (C4 (Web Text))

Max Activating Token Index: 230

Text #15

Max Range: 0.7080. Min Range: -0.7080

Max Act: 0.5817. Min Act: -0.0001

Data Index: 144979 (C4 (Web Text))

Max Activating Token Index: 313

Text #16

Max Range: 0.7080. Min Range: -0.7080

Max Act: 0.5757. Min Act: -0.0001

Data Index: 1030326 (C4 (Web Text))

Max Activating Token Index: 712

Text #17

Max Range: 0.7080. Min Range: -0.7080

Max Act: 0.5437. Min Act: -0.0001

Data Index: 961829 (C4 (Web Text))

Max Activating Token Index: 364

Text #18

Max Range: 0.7080. Min Range: -0.7080

Max Act: 0.5405. Min Act: -0.0001

Data Index: 713472 (C4 (Web Text))

Max Activating Token Index: 1012

Text #19

Max Range: 0.7080. Min Range: -0.7080

Max Act: 0.5743. Min Act: -0.0001

Data Index: 1169530 (C4 (Web Text))

Max Activating Token Index: 693