Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3640 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.4885. Min Range: -0.4885

Max Act: 0.4885. Min Act: -0.0000

Data Index: 276206 (C4 (Web Text))

Max Activating Token Index: 706

Text #1

Max Range: 0.4885. Min Range: -0.4885

Max Act: 0.4289. Min Act: -0.0000

Data Index: 169499 (C4 (Web Text))

Max Activating Token Index: 407

Text #2

Max Range: 0.4885. Min Range: -0.4885

Max Act: 0.4250. Min Act: -0.0000

Data Index: 123710 (C4 (Web Text))

Max Activating Token Index: 650

Text #3

Max Range: 0.4885. Min Range: -0.4885

Max Act: 0.4299. Min Act: -0.0000

Data Index: 353677 (C4 (Web Text))

Max Activating Token Index: 916

Text #4

Max Range: 0.4885. Min Range: -0.4885

Max Act: 0.3915. Min Act: -0.0000

Data Index: 73602 (C4 (Web Text))

Max Activating Token Index: 456

Text #5

Max Range: 0.4885. Min Range: -0.4885

Max Act: 0.4046. Min Act: -0.0000

Data Index: 665917 (C4 (Web Text))

Max Activating Token Index: 91

Text #6

Max Range: 0.4885. Min Range: -0.4885

Max Act: 0.3865. Min Act: -0.0000

Data Index: 201264 (C4 (Web Text))

Max Activating Token Index: 926

Text #7

Max Range: 0.4885. Min Range: -0.4885

Max Act: 0.3688. Min Act: -0.0000

Data Index: 927667 (C4 (Web Text))

Max Activating Token Index: 829

Text #8

Max Range: 0.4885. Min Range: -0.4885

Max Act: 0.3805. Min Act: -0.0000

Data Index: 393463 (C4 (Web Text))

Max Activating Token Index: 359

Text #9

Max Range: 0.4885. Min Range: -0.4885

Max Act: 0.3724. Min Act: -0.0000

Data Index: 292636 (C4 (Web Text))

Max Activating Token Index: 235

Text #10

Max Range: 0.4885. Min Range: -0.4885

Max Act: 0.3655. Min Act: -0.0000

Data Index: 1009730 (C4 (Web Text))

Max Activating Token Index: 467

Text #11

Max Range: 0.4885. Min Range: -0.4885

Max Act: 0.3543. Min Act: -0.0000

Data Index: 702752 (C4 (Web Text))

Max Activating Token Index: 136

Text #12

Max Range: 0.4885. Min Range: -0.4885

Max Act: 0.3850. Min Act: -0.0000

Data Index: 1251373 (C4 (Web Text))

Max Activating Token Index: 561

Text #13

Max Range: 0.4885. Min Range: -0.4885

Max Act: 0.3731. Min Act: -0.0000

Data Index: 674704 (C4 (Web Text))

Max Activating Token Index: 954

Text #14

Max Range: 0.4885. Min Range: -0.4885

Max Act: 0.3655. Min Act: -0.0000

Data Index: 75510 (C4 (Web Text))

Max Activating Token Index: 479

Text #15

Max Range: 0.4885. Min Range: -0.4885

Max Act: 0.3650. Min Act: -0.0000

Data Index: 1158025 (C4 (Web Text))

Max Activating Token Index: 697

Text #16

Max Range: 0.4885. Min Range: -0.4885

Max Act: 0.3787. Min Act: -0.0000

Data Index: 869861 (C4 (Web Text))

Max Activating Token Index: 57

Text #17

Max Range: 0.4885. Min Range: -0.4885

Max Act: 0.3488. Min Act: -0.0000

Data Index: 1207636 (C4 (Web Text))

Max Activating Token Index: 530

Text #18

Max Range: 0.4885. Min Range: -0.4885

Max Act: 0.3445. Min Act: -0.0000

Data Index: 837171 (C4 (Web Text))

Max Activating Token Index: 783

Text #19

Max Range: 0.4885. Min Range: -0.4885

Max Act: 0.3645. Min Act: -0.0000

Data Index: 277754 (C4 (Web Text))

Max Activating Token Index: 559