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

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

Neuron 649 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: 1.5112. Min Range: -1.5112

Max Act: 1.5112. Min Act: -0.0000

Data Index: 1220901 (C4 (Web Text))

Max Activating Token Index: 1015

Text #1

Max Range: 1.5112. Min Range: -1.5112

Max Act: 1.3246. Min Act: -0.0000

Data Index: 1171432 (C4 (Web Text))

Max Activating Token Index: 845

Text #2

Max Range: 1.5112. Min Range: -1.5112

Max Act: 1.2564. Min Act: -0.0000

Data Index: 818010 (C4 (Web Text))

Max Activating Token Index: 299

Text #3

Max Range: 1.5112. Min Range: -1.5112

Max Act: 1.2147. Min Act: -0.0000

Data Index: 949583 (C4 (Web Text))

Max Activating Token Index: 368

Text #4

Max Range: 1.5112. Min Range: -1.5112

Max Act: 1.1567. Min Act: -0.0000

Data Index: 315165 (C4 (Web Text))

Max Activating Token Index: 333

Text #5

Max Range: 1.5112. Min Range: -1.5112

Max Act: 1.1810. Min Act: -0.0000

Data Index: 290 (C4 (Web Text))

Max Activating Token Index: 191

Text #6

Max Range: 1.5112. Min Range: -1.5112

Max Act: 1.0977. Min Act: 0.0001

Data Index: 40372 (C4 (Web Text))

Max Activating Token Index: 212

Text #7

Max Range: 1.5112. Min Range: -1.5112

Max Act: 1.0893. Min Act: -0.0000

Data Index: 603957 (C4 (Web Text))

Max Activating Token Index: 239

Text #8

Max Range: 1.5112. Min Range: -1.5112

Max Act: 1.0038. Min Act: -0.0000

Data Index: 451783 (C4 (Web Text))

Max Activating Token Index: 82

Text #9

Max Range: 1.5112. Min Range: -1.5112

Max Act: 0.9919. Min Act: -0.0000

Data Index: 440757 (C4 (Web Text))

Max Activating Token Index: 819

Text #10

Max Range: 1.5112. Min Range: -1.5112

Max Act: 1.0342. Min Act: -0.0000

Data Index: 368922 (C4 (Web Text))

Max Activating Token Index: 586

Text #11

Max Range: 1.5112. Min Range: -1.5112

Max Act: 1.0746. Min Act: -0.0000

Data Index: 451511 (C4 (Web Text))

Max Activating Token Index: 957

Text #12

Max Range: 1.5112. Min Range: -1.5112

Max Act: 0.9978. Min Act: -0.0000

Data Index: 45347 (C4 (Web Text))

Max Activating Token Index: 491

Text #13

Max Range: 1.5112. Min Range: -1.5112

Max Act: 0.9962. Min Act: -0.0000

Data Index: 174741 (C4 (Web Text))

Max Activating Token Index: 589

Text #14

Max Range: 1.5112. Min Range: -1.5112

Max Act: 0.9727. Min Act: -0.0000

Data Index: 345244 (C4 (Web Text))

Max Activating Token Index: 321

Text #15

Max Range: 1.5112. Min Range: -1.5112

Max Act: 0.9754. Min Act: -0.0000

Data Index: 100367 (C4 (Web Text))

Max Activating Token Index: 453

Text #16

Max Range: 1.5112. Min Range: -1.5112

Max Act: 1.0331. Min Act: -0.0000

Data Index: 915865 (C4 (Web Text))

Max Activating Token Index: 193

Text #17

Max Range: 1.5112. Min Range: -1.5112

Max Act: 0.8976. Min Act: -0.0000

Data Index: 93838 (C4 (Web Text))

Max Activating Token Index: 783

Text #18

Max Range: 1.5112. Min Range: -1.5112

Max Act: 0.9608. Min Act: -0.0000

Data Index: 384808 (C4 (Web Text))

Max Activating Token Index: 158

Text #19

Max Range: 1.5112. Min Range: -1.5112

Max Act: 0.9429. Min Act: -0.0000

Data Index: 719350 (C4 (Web Text))

Max Activating Token Index: 219