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

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

Neuron 3887 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9380. Min Range: -2.9380

Max Act: 2.9380. Min Act: -0.0000

Data Index: 970680 (C4 (Web Text))

Max Activating Token Index: 269

Text #1

Max Range: 2.9380. Min Range: -2.9380

Max Act: 2.8387. Min Act: -0.0000

Data Index: 361365 (C4 (Web Text))

Max Activating Token Index: 968

Text #2

Max Range: 2.9380. Min Range: -2.9380

Max Act: 2.6018. Min Act: -0.0000

Data Index: 911904 (C4 (Web Text))

Max Activating Token Index: 591

Text #3

Max Range: 2.9380. Min Range: -2.9380

Max Act: 2.8024. Min Act: -0.0000

Data Index: 450237 (C4 (Web Text))

Max Activating Token Index: 1021

Text #4

Max Range: 2.9380. Min Range: -2.9380

Max Act: 2.5899. Min Act: -0.0000

Data Index: 118013 (C4 (Web Text))

Max Activating Token Index: 673

Text #5

Max Range: 2.9380. Min Range: -2.9380

Max Act: 2.4571. Min Act: -0.0000

Data Index: 1157920 (C4 (Web Text))

Max Activating Token Index: 121

Text #6

Max Range: 2.9380. Min Range: -2.9380

Max Act: 2.4498. Min Act: -0.0000

Data Index: 1002831 (C4 (Web Text))

Max Activating Token Index: 640

Text #7

Max Range: 2.9380. Min Range: -2.9380

Max Act: 2.4281. Min Act: -0.0000

Data Index: 120417 (C4 (Web Text))

Max Activating Token Index: 225

Text #8

Max Range: 2.9380. Min Range: -2.9380

Max Act: 2.5581. Min Act: -0.0000

Data Index: 645094 (C4 (Web Text))

Max Activating Token Index: 1000

Text #9

Max Range: 2.9380. Min Range: -2.9380

Max Act: 2.5963. Min Act: -0.0000

Data Index: 462397 (C4 (Web Text))

Max Activating Token Index: 688

Text #10

Max Range: 2.9380. Min Range: -2.9380

Max Act: 2.3437. Min Act: -0.0000

Data Index: 280110 (C4 (Web Text))

Max Activating Token Index: 95

Text #11

Max Range: 2.9380. Min Range: -2.9380

Max Act: 2.3147. Min Act: -0.0000

Data Index: 638929 (C4 (Web Text))

Max Activating Token Index: 150

Text #12

Max Range: 2.9380. Min Range: -2.9380

Max Act: 2.4455. Min Act: -0.0000

Data Index: 1114149 (C4 (Web Text))

Max Activating Token Index: 800

Text #13

Max Range: 2.9380. Min Range: -2.9380

Max Act: 2.4308. Min Act: -0.0000

Data Index: 146241 (C4 (Web Text))

Max Activating Token Index: 74

Text #14

Max Range: 2.9380. Min Range: -2.9380

Max Act: 2.4017. Min Act: -0.0000

Data Index: 67515 (C4 (Web Text))

Max Activating Token Index: 308

Text #15

Max Range: 2.9380. Min Range: -2.9380

Max Act: 2.3740. Min Act: -0.0000

Data Index: 1345811 (C4 (Web Text))

Max Activating Token Index: 301

Text #16

Max Range: 2.9380. Min Range: -2.9380

Max Act: 2.3662. Min Act: -0.0000

Data Index: 1240706 (C4 (Web Text))

Max Activating Token Index: 289

Text #17

Max Range: 2.9380. Min Range: -2.9380

Max Act: 2.3423. Min Act: -0.0000

Data Index: 671266 (C4 (Web Text))

Max Activating Token Index: 63

Text #18

Max Range: 2.9380. Min Range: -2.9380

Max Act: 2.3089. Min Act: -0.0000

Data Index: 899348 (C4 (Web Text))

Max Activating Token Index: 864

Text #19

Max Range: 2.9380. Min Range: -2.9380

Max Act: 2.1871. Min Act: -0.0000

Data Index: 1024191 (C4 (Web Text))

Max Activating Token Index: 139