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

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

Neuron 4812 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8688. Min Range: -2.8688

Max Act: 2.8688. Min Act: -0.0000

Data Index: 1247565 (C4 (Web Text))

Max Activating Token Index: 185

Text #1

Max Range: 2.8688. Min Range: -2.8688

Max Act: 2.7912. Min Act: -0.0000

Data Index: 422062 (C4 (Web Text))

Max Activating Token Index: 734

Text #2

Max Range: 2.8688. Min Range: -2.8688

Max Act: 2.5311. Min Act: -0.0000

Data Index: 507371 (C4 (Web Text))

Max Activating Token Index: 615

Text #3

Max Range: 2.8688. Min Range: -2.8688

Max Act: 2.6159. Min Act: -0.0000

Data Index: 241443 (C4 (Web Text))

Max Activating Token Index: 714

Text #4

Max Range: 2.8688. Min Range: -2.8688

Max Act: 2.6584. Min Act: -0.0000

Data Index: 1248725 (C4 (Web Text))

Max Activating Token Index: 113

Text #5

Max Range: 2.8688. Min Range: -2.8688

Max Act: 2.5095. Min Act: -0.0000

Data Index: 52517 (C4 (Web Text))

Max Activating Token Index: 532

Text #6

Max Range: 2.8688. Min Range: -2.8688

Max Act: 2.3384. Min Act: -0.0000

Data Index: 575133 (C4 (Web Text))

Max Activating Token Index: 624

Text #7

Max Range: 2.8688. Min Range: -2.8688

Max Act: 2.5749. Min Act: -0.0000

Data Index: 976364 (C4 (Web Text))

Max Activating Token Index: 421

Text #8

Max Range: 2.8688. Min Range: -2.8688

Max Act: 2.4158. Min Act: -0.0000

Data Index: 1122371 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 2.8688. Min Range: -2.8688

Max Act: 2.3903. Min Act: -0.0000

Data Index: 713513 (C4 (Web Text))

Max Activating Token Index: 425

Text #10

Max Range: 2.8688. Min Range: -2.8688

Max Act: 2.3780. Min Act: -0.0000

Data Index: 393577 (C4 (Web Text))

Max Activating Token Index: 68

Text #11

Max Range: 2.8688. Min Range: -2.8688

Max Act: 2.4519. Min Act: -0.0000

Data Index: 1219583 (C4 (Web Text))

Max Activating Token Index: 765

Text #12

Max Range: 2.8688. Min Range: -2.8688

Max Act: 2.1811. Min Act: -0.0000

Data Index: 245663 (C4 (Web Text))

Max Activating Token Index: 169

Text #13

Max Range: 2.8688. Min Range: -2.8688

Max Act: 2.3014. Min Act: -0.0000

Data Index: 937892 (C4 (Web Text))

Max Activating Token Index: 993

Text #14

Max Range: 2.8688. Min Range: -2.8688

Max Act: 2.2546. Min Act: -0.0000

Data Index: 677750 (C4 (Web Text))

Max Activating Token Index: 71

Text #15

Max Range: 2.8688. Min Range: -2.8688

Max Act: 2.2206. Min Act: -0.0000

Data Index: 929603 (C4 (Web Text))

Max Activating Token Index: 187

Text #16

Max Range: 2.8688. Min Range: -2.8688

Max Act: 2.1549. Min Act: -0.0000

Data Index: 102473 (C4 (Web Text))

Max Activating Token Index: 96

Text #17

Max Range: 2.8688. Min Range: -2.8688

Max Act: 2.1479. Min Act: -0.0000

Data Index: 894944 (C4 (Web Text))

Max Activating Token Index: 278

Text #18

Max Range: 2.8688. Min Range: -2.8688

Max Act: 2.1537. Min Act: -0.0000

Data Index: 980022 (C4 (Web Text))

Max Activating Token Index: 634

Text #19

Max Range: 2.8688. Min Range: -2.8688

Max Act: 1.9983. Min Act: -0.0000

Data Index: 1116393 (C4 (Web Text))

Max Activating Token Index: 812