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

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

Neuron 4733 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4347. Min Range: -0.4347

Max Act: 0.4347. Min Act: -0.0000

Data Index: 1158255 (C4 (Web Text))

Max Activating Token Index: 754

Text #1

Max Range: 0.4347. Min Range: -0.4347

Max Act: 0.4047. Min Act: -0.0000

Data Index: 622237 (C4 (Web Text))

Max Activating Token Index: 361

Text #2

Max Range: 0.4347. Min Range: -0.4347

Max Act: 0.3761. Min Act: -0.0000

Data Index: 754982 (C4 (Web Text))

Max Activating Token Index: 946

Text #3

Max Range: 0.4347. Min Range: -0.4347

Max Act: 0.4158. Min Act: -0.0000

Data Index: 670472 (C4 (Web Text))

Max Activating Token Index: 963

Text #4

Max Range: 0.4347. Min Range: -0.4347

Max Act: 0.3751. Min Act: -0.0000

Data Index: 1191227 (C4 (Web Text))

Max Activating Token Index: 350

Text #5

Max Range: 0.4347. Min Range: -0.4347

Max Act: 0.3532. Min Act: -0.0000

Data Index: 1179983 (C4 (Web Text))

Max Activating Token Index: 711

Text #6

Max Range: 0.4347. Min Range: -0.4347

Max Act: 0.3571. Min Act: -0.0000

Data Index: 1236852 (C4 (Web Text))

Max Activating Token Index: 336

Text #7

Max Range: 0.4347. Min Range: -0.4347

Max Act: 0.3078. Min Act: -0.0000

Data Index: 434257 (C4 (Web Text))

Max Activating Token Index: 580

Text #8

Max Range: 0.4347. Min Range: -0.4347

Max Act: 0.3439. Min Act: -0.0000

Data Index: 550673 (C4 (Web Text))

Max Activating Token Index: 86

Text #9

Max Range: 0.4347. Min Range: -0.4347

Max Act: 0.3220. Min Act: -0.0000

Data Index: 1438315 (Python Code)

Max Activating Token Index: 670

Text #10

Max Range: 0.4347. Min Range: -0.4347

Max Act: 0.3112. Min Act: -0.0000

Data Index: 749704 (C4 (Web Text))

Max Activating Token Index: 48

Text #11

Max Range: 0.4347. Min Range: -0.4347

Max Act: 0.3125. Min Act: -0.0000

Data Index: 750173 (C4 (Web Text))

Max Activating Token Index: 775

Text #12

Max Range: 0.4347. Min Range: -0.4347

Max Act: 0.3083. Min Act: -0.0000

Data Index: 1511703 (Python Code)

Max Activating Token Index: 70

Text #13

Max Range: 0.4347. Min Range: -0.4347

Max Act: 0.3066. Min Act: -0.0000

Data Index: 351284 (C4 (Web Text))

Max Activating Token Index: 834

Text #14

Max Range: 0.4347. Min Range: -0.4347

Max Act: 0.2719. Min Act: -0.0000

Data Index: 464759 (C4 (Web Text))

Max Activating Token Index: 112

Text #15

Max Range: 0.4347. Min Range: -0.4347

Max Act: 0.2832. Min Act: -0.0000

Data Index: 325707 (C4 (Web Text))

Max Activating Token Index: 975

Text #16

Max Range: 0.4347. Min Range: -0.4347

Max Act: 0.2832. Min Act: -0.0000

Data Index: 136249 (C4 (Web Text))

Max Activating Token Index: 406

Text #17

Max Range: 0.4347. Min Range: -0.4347

Max Act: 0.2791. Min Act: -0.0000

Data Index: 945523 (C4 (Web Text))

Max Activating Token Index: 859

Text #18

Max Range: 0.4347. Min Range: -0.4347

Max Act: 0.2913. Min Act: -0.0000

Data Index: 654175 (C4 (Web Text))

Max Activating Token Index: 383

Text #19

Max Range: 0.4347. Min Range: -0.4347

Max Act: 0.2663. Min Act: -0.0000

Data Index: 1570679 (Python Code)

Max Activating Token Index: 658