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

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

Neuron 1881 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: 1.9867. Min Range: -1.9867

Max Act: 1.9867. Min Act: -0.0000

Data Index: 794169 (C4 (Web Text))

Max Activating Token Index: 380

Text #1

Max Range: 1.9867. Min Range: -1.9867

Max Act: 1.7834. Min Act: -0.0000

Data Index: 539601 (C4 (Web Text))

Max Activating Token Index: 979

Text #2

Max Range: 1.9867. Min Range: -1.9867

Max Act: 1.6681. Min Act: -0.0000

Data Index: 493977 (C4 (Web Text))

Max Activating Token Index: 764

Text #3

Max Range: 1.9867. Min Range: -1.9867

Max Act: 1.5755. Min Act: -0.0000

Data Index: 651417 (C4 (Web Text))

Max Activating Token Index: 147

Text #4

Max Range: 1.9867. Min Range: -1.9867

Max Act: 1.4846. Min Act: 0.0000

Data Index: 679146 (C4 (Web Text))

Max Activating Token Index: 817

Text #5

Max Range: 1.9867. Min Range: -1.9867

Max Act: 1.6290. Min Act: -0.0000

Data Index: 934235 (C4 (Web Text))

Max Activating Token Index: 729

Text #6

Max Range: 1.9867. Min Range: -1.9867

Max Act: 1.5451. Min Act: -0.0000

Data Index: 312434 (C4 (Web Text))

Max Activating Token Index: 150

Text #7

Max Range: 1.9867. Min Range: -1.9867

Max Act: 1.4336. Min Act: -0.0000

Data Index: 31289 (C4 (Web Text))

Max Activating Token Index: 171

Text #8

Max Range: 1.9867. Min Range: -1.9867

Max Act: 1.5320. Min Act: -0.0000

Data Index: 890307 (C4 (Web Text))

Max Activating Token Index: 270

Text #9

Max Range: 1.9867. Min Range: -1.9867

Max Act: 1.4338. Min Act: -0.0000

Data Index: 450871 (C4 (Web Text))

Max Activating Token Index: 20

Text #10

Max Range: 1.9867. Min Range: -1.9867

Max Act: 1.4386. Min Act: -0.0000

Data Index: 859407 (C4 (Web Text))

Max Activating Token Index: 144

Text #11

Max Range: 1.9867. Min Range: -1.9867

Max Act: 1.4194. Min Act: -0.0000

Data Index: 807979 (C4 (Web Text))

Max Activating Token Index: 163

Text #12

Max Range: 1.9867. Min Range: -1.9867

Max Act: 1.4012. Min Act: -0.0000

Data Index: 1054759 (C4 (Web Text))

Max Activating Token Index: 847

Text #13

Max Range: 1.9867. Min Range: -1.9867

Max Act: 1.4030. Min Act: -0.0000

Data Index: 124195 (C4 (Web Text))

Max Activating Token Index: 717

Text #14

Max Range: 1.9867. Min Range: -1.9867

Max Act: 1.3943. Min Act: 0.0000

Data Index: 879418 (C4 (Web Text))

Max Activating Token Index: 57

Text #15

Max Range: 1.9867. Min Range: -1.9867

Max Act: 1.4660. Min Act: -0.0000

Data Index: 1005604 (C4 (Web Text))

Max Activating Token Index: 1000

Text #16

Max Range: 1.9867. Min Range: -1.9867

Max Act: 1.3868. Min Act: -0.0000

Data Index: 556045 (C4 (Web Text))

Max Activating Token Index: 85

Text #17

Max Range: 1.9867. Min Range: -1.9867

Max Act: 1.3734. Min Act: -0.0000

Data Index: 592612 (C4 (Web Text))

Max Activating Token Index: 327

Text #18

Max Range: 1.9867. Min Range: -1.9867

Max Act: 1.3449. Min Act: -0.0000

Data Index: 1135094 (C4 (Web Text))

Max Activating Token Index: 444

Text #19

Max Range: 1.9867. Min Range: -1.9867

Max Act: 1.3403. Min Act: -0.0000

Data Index: 580596 (C4 (Web Text))

Max Activating Token Index: 552