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

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

Neuron 2720 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4475. Min Range: -0.4475

Max Act: 0.4475. Min Act: -0.0000

Data Index: 1359152 (C4 (Web Text))

Max Activating Token Index: 511

Text #1

Max Range: 0.4475. Min Range: -0.4475

Max Act: 0.3890. Min Act: -0.0000

Data Index: 950349 (C4 (Web Text))

Max Activating Token Index: 291

Text #2

Max Range: 0.4475. Min Range: -0.4475

Max Act: 0.3562. Min Act: -0.0000

Data Index: 813531 (C4 (Web Text))

Max Activating Token Index: 464

Text #3

Max Range: 0.4475. Min Range: -0.4475

Max Act: 0.3343. Min Act: -0.0000

Data Index: 556229 (C4 (Web Text))

Max Activating Token Index: 666

Text #4

Max Range: 0.4475. Min Range: -0.4475

Max Act: 0.3531. Min Act: -0.0000

Data Index: 478376 (C4 (Web Text))

Max Activating Token Index: 808

Text #5

Max Range: 0.4475. Min Range: -0.4475

Max Act: 0.3181. Min Act: 0.0000

Data Index: 1201726 (C4 (Web Text))

Max Activating Token Index: 790

Text #6

Max Range: 0.4475. Min Range: -0.4475

Max Act: 0.3315. Min Act: -0.0000

Data Index: 949196 (C4 (Web Text))

Max Activating Token Index: 449

Text #7

Max Range: 0.4475. Min Range: -0.4475

Max Act: 0.3280. Min Act: 0.0000

Data Index: 515746 (C4 (Web Text))

Max Activating Token Index: 681

Text #8

Max Range: 0.4475. Min Range: -0.4475

Max Act: 0.3498. Min Act: 0.0000

Data Index: 833329 (C4 (Web Text))

Max Activating Token Index: 209

Text #9

Max Range: 0.4475. Min Range: -0.4475

Max Act: 0.3310. Min Act: -0.0000

Data Index: 160332 (C4 (Web Text))

Max Activating Token Index: 801

Text #10

Max Range: 0.4475. Min Range: -0.4475

Max Act: 0.3104. Min Act: 0.0000

Data Index: 1165440 (C4 (Web Text))

Max Activating Token Index: 800

Text #11

Max Range: 0.4475. Min Range: -0.4475

Max Act: 0.3073. Min Act: -0.0000

Data Index: 1128645 (C4 (Web Text))

Max Activating Token Index: 55

Text #12

Max Range: 0.4475. Min Range: -0.4475

Max Act: 0.2977. Min Act: -0.0000

Data Index: 954654 (C4 (Web Text))

Max Activating Token Index: 762

Text #13

Max Range: 0.4475. Min Range: -0.4475

Max Act: 0.3090. Min Act: 0.0000

Data Index: 1075009 (C4 (Web Text))

Max Activating Token Index: 725

Text #14

Max Range: 0.4475. Min Range: -0.4475

Max Act: 0.2887. Min Act: -0.0000

Data Index: 199429 (C4 (Web Text))

Max Activating Token Index: 419

Text #15

Max Range: 0.4475. Min Range: -0.4475

Max Act: 0.3001. Min Act: 0.0000

Data Index: 190788 (C4 (Web Text))

Max Activating Token Index: 944

Text #16

Max Range: 0.4475. Min Range: -0.4475

Max Act: 0.2952. Min Act: -0.0000

Data Index: 548033 (C4 (Web Text))

Max Activating Token Index: 38

Text #17

Max Range: 0.4475. Min Range: -0.4475

Max Act: 0.2918. Min Act: -0.0000

Data Index: 1260681 (C4 (Web Text))

Max Activating Token Index: 722

Text #18

Max Range: 0.4475. Min Range: -0.4475

Max Act: 0.2935. Min Act: -0.0000

Data Index: 682729 (C4 (Web Text))

Max Activating Token Index: 845

Text #19

Max Range: 0.4475. Min Range: -0.4475

Max Act: 0.2857. Min Act: -0.0000

Data Index: 1357791 (C4 (Web Text))

Max Activating Token Index: 105