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

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

Neuron 382 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: 0.5826. Min Range: -0.5826

Max Act: 0.5826. Min Act: -0.0000

Data Index: 1220154 (C4 (Web Text))

Max Activating Token Index: 82

Text #1

Max Range: 0.5826. Min Range: -0.5826

Max Act: 0.4690. Min Act: -0.0000

Data Index: 1359041 (C4 (Web Text))

Max Activating Token Index: 661

Text #2

Max Range: 0.5826. Min Range: -0.5826

Max Act: 0.4181. Min Act: -0.0000

Data Index: 873623 (C4 (Web Text))

Max Activating Token Index: 994

Text #3

Max Range: 0.5826. Min Range: -0.5826

Max Act: 0.4661. Min Act: -0.0000

Data Index: 88687 (C4 (Web Text))

Max Activating Token Index: 882

Text #4

Max Range: 0.5826. Min Range: -0.5826

Max Act: 0.4535. Min Act: -0.0000

Data Index: 580928 (C4 (Web Text))

Max Activating Token Index: 1008

Text #5

Max Range: 0.5826. Min Range: -0.5826

Max Act: 0.4897. Min Act: -0.0000

Data Index: 391832 (C4 (Web Text))

Max Activating Token Index: 31

Text #6

Max Range: 0.5826. Min Range: -0.5826

Max Act: 0.4017. Min Act: -0.0000

Data Index: 775044 (C4 (Web Text))

Max Activating Token Index: 649

Text #7

Max Range: 0.5826. Min Range: -0.5826

Max Act: 0.4079. Min Act: -0.0000

Data Index: 1095497 (C4 (Web Text))

Max Activating Token Index: 240

Text #8

Max Range: 0.5826. Min Range: -0.5826

Max Act: 0.4135. Min Act: -0.0000

Data Index: 178453 (C4 (Web Text))

Max Activating Token Index: 266

Text #9

Max Range: 0.5826. Min Range: -0.5826

Max Act: 0.3981. Min Act: -0.0000

Data Index: 895167 (C4 (Web Text))

Max Activating Token Index: 109

Text #10

Max Range: 0.5826. Min Range: -0.5826

Max Act: 0.3784. Min Act: -0.0000

Data Index: 1179945 (C4 (Web Text))

Max Activating Token Index: 426

Text #11

Max Range: 0.5826. Min Range: -0.5826

Max Act: 0.3519. Min Act: -0.0000

Data Index: 861981 (C4 (Web Text))

Max Activating Token Index: 278

Text #12

Max Range: 0.5826. Min Range: -0.5826

Max Act: 0.3137. Min Act: -0.0000

Data Index: 450054 (C4 (Web Text))

Max Activating Token Index: 536

Text #13

Max Range: 0.5826. Min Range: -0.5826

Max Act: 0.3587. Min Act: -0.0000

Data Index: 628192 (C4 (Web Text))

Max Activating Token Index: 388

Text #14

Max Range: 0.5826. Min Range: -0.5826

Max Act: 0.3598. Min Act: -0.0000

Data Index: 253777 (C4 (Web Text))

Max Activating Token Index: 75

Text #15

Max Range: 0.5826. Min Range: -0.5826

Max Act: 0.3433. Min Act: -0.0000

Data Index: 981514 (C4 (Web Text))

Max Activating Token Index: 137

Text #16

Max Range: 0.5826. Min Range: -0.5826

Max Act: 0.3485. Min Act: -0.0000

Data Index: 139456 (C4 (Web Text))

Max Activating Token Index: 408

Text #17

Max Range: 0.5826. Min Range: -0.5826

Max Act: 0.2845. Min Act: -0.0000

Data Index: 170733 (C4 (Web Text))

Max Activating Token Index: 386

Text #18

Max Range: 0.5826. Min Range: -0.5826

Max Act: 0.3141. Min Act: -0.0000

Data Index: 32590 (C4 (Web Text))

Max Activating Token Index: 761

Text #19

Max Range: 0.5826. Min Range: -0.5826

Max Act: 0.2984. Min Act: -0.0000

Data Index: 1277647 (C4 (Web Text))

Max Activating Token Index: 517