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

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

Neuron 3473 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3817. Min Range: -0.3817

Max Act: 0.3784. Min Act: -0.0000

Data Index: 321345 (C4 (Web Text))

Max Activating Token Index: 106

Text #1

Max Range: 0.3817. Min Range: -0.3817

Max Act: 0.3817. Min Act: -0.0000

Data Index: 430366 (C4 (Web Text))

Max Activating Token Index: 848

Text #2

Max Range: 0.3817. Min Range: -0.3817

Max Act: 0.3356. Min Act: -0.0000

Data Index: 651744 (C4 (Web Text))

Max Activating Token Index: 147

Text #3

Max Range: 0.3817. Min Range: -0.3817

Max Act: 0.3326. Min Act: -0.0001

Data Index: 281715 (C4 (Web Text))

Max Activating Token Index: 629

Text #4

Max Range: 0.3817. Min Range: -0.3817

Max Act: 0.3127. Min Act: -0.0000

Data Index: 276897 (C4 (Web Text))

Max Activating Token Index: 542

Text #5

Max Range: 0.3817. Min Range: -0.3817

Max Act: 0.2977. Min Act: -0.0000

Data Index: 860253 (C4 (Web Text))

Max Activating Token Index: 328

Text #6

Max Range: 0.3817. Min Range: -0.3817

Max Act: 0.3175. Min Act: -0.0000

Data Index: 266349 (C4 (Web Text))

Max Activating Token Index: 1004

Text #7

Max Range: 0.3817. Min Range: -0.3817

Max Act: 0.3051. Min Act: -0.0001

Data Index: 1250141 (C4 (Web Text))

Max Activating Token Index: 147

Text #8

Max Range: 0.3817. Min Range: -0.3817

Max Act: 0.3006. Min Act: -0.0000

Data Index: 1254431 (C4 (Web Text))

Max Activating Token Index: 509

Text #9

Max Range: 0.3817. Min Range: -0.3817

Max Act: 0.2833. Min Act: -0.0000

Data Index: 130836 (C4 (Web Text))

Max Activating Token Index: 430

Text #10

Max Range: 0.3817. Min Range: -0.3817

Max Act: 0.2813. Min Act: -0.0000

Data Index: 1326135 (C4 (Web Text))

Max Activating Token Index: 452

Text #11

Max Range: 0.3817. Min Range: -0.3817

Max Act: 0.2967. Min Act: -0.0001

Data Index: 661241 (C4 (Web Text))

Max Activating Token Index: 719

Text #12

Max Range: 0.3817. Min Range: -0.3817

Max Act: 0.2808. Min Act: -0.0000

Data Index: 102016 (C4 (Web Text))

Max Activating Token Index: 497

Text #13

Max Range: 0.3817. Min Range: -0.3817

Max Act: 0.3004. Min Act: -0.0000

Data Index: 1055730 (C4 (Web Text))

Max Activating Token Index: 179

Text #14

Max Range: 0.3817. Min Range: -0.3817

Max Act: 0.2853. Min Act: -0.0000

Data Index: 1349993 (C4 (Web Text))

Max Activating Token Index: 815

Text #15

Max Range: 0.3817. Min Range: -0.3817

Max Act: 0.2840. Min Act: -0.0000

Data Index: 1167244 (C4 (Web Text))

Max Activating Token Index: 125

Text #16

Max Range: 0.3817. Min Range: -0.3817

Max Act: 0.2561. Min Act: -0.0000

Data Index: 993980 (C4 (Web Text))

Max Activating Token Index: 633

Text #17

Max Range: 0.3817. Min Range: -0.3817

Max Act: 0.2754. Min Act: -0.0000

Data Index: 306440 (C4 (Web Text))

Max Activating Token Index: 85

Text #18

Max Range: 0.3817. Min Range: -0.3817

Max Act: 0.2461. Min Act: -0.0000

Data Index: 1231709 (C4 (Web Text))

Max Activating Token Index: 699

Text #19

Max Range: 0.3817. Min Range: -0.3817

Max Act: 0.2507. Min Act: -0.0000

Data Index: 822085 (C4 (Web Text))

Max Activating Token Index: 272