Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2159 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.5317. Min Range: -0.5317

Max Act: 0.5317. Min Act: -0.0000

Data Index: 821625 (C4 (Web Text))

Max Activating Token Index: 56

Text #1

Max Range: 0.5317. Min Range: -0.5317

Max Act: 0.4899. Min Act: -0.0000

Data Index: 800828 (C4 (Web Text))

Max Activating Token Index: 80

Text #2

Max Range: 0.5317. Min Range: -0.5317

Max Act: 0.4819. Min Act: -0.0000

Data Index: 699638 (C4 (Web Text))

Max Activating Token Index: 150

Text #3

Max Range: 0.5317. Min Range: -0.5317

Max Act: 0.4221. Min Act: -0.0000

Data Index: 467990 (C4 (Web Text))

Max Activating Token Index: 121

Text #4

Max Range: 0.5317. Min Range: -0.5317

Max Act: 0.3958. Min Act: -0.0000

Data Index: 167058 (C4 (Web Text))

Max Activating Token Index: 993

Text #5

Max Range: 0.5317. Min Range: -0.5317

Max Act: 0.4024. Min Act: -0.0000

Data Index: 1296308 (C4 (Web Text))

Max Activating Token Index: 883

Text #6

Max Range: 0.5317. Min Range: -0.5317

Max Act: 0.3385. Min Act: -0.0000

Data Index: 203045 (C4 (Web Text))

Max Activating Token Index: 840

Text #7

Max Range: 0.5317. Min Range: -0.5317

Max Act: 0.3996. Min Act: -0.0000

Data Index: 585167 (C4 (Web Text))

Max Activating Token Index: 119

Text #8

Max Range: 0.5317. Min Range: -0.5317

Max Act: 0.3519. Min Act: -0.0000

Data Index: 285497 (C4 (Web Text))

Max Activating Token Index: 258

Text #9

Max Range: 0.5317. Min Range: -0.5317

Max Act: 0.3834. Min Act: 0.0000

Data Index: 228997 (C4 (Web Text))

Max Activating Token Index: 100

Text #10

Max Range: 0.5317. Min Range: -0.5317

Max Act: 0.3584. Min Act: -0.0000

Data Index: 208917 (C4 (Web Text))

Max Activating Token Index: 768

Text #11

Max Range: 0.5317. Min Range: -0.5317

Max Act: 0.3777. Min Act: -0.0000

Data Index: 920365 (C4 (Web Text))

Max Activating Token Index: 93

Text #12

Max Range: 0.5317. Min Range: -0.5317

Max Act: 0.3534. Min Act: -0.0000

Data Index: 1367285 (Python Code)

Max Activating Token Index: 502

Text #13

Max Range: 0.5317. Min Range: -0.5317

Max Act: 0.3377. Min Act: -0.0000

Data Index: 256863 (C4 (Web Text))

Max Activating Token Index: 559

Text #14

Max Range: 0.5317. Min Range: -0.5317

Max Act: 0.3286. Min Act: -0.0000

Data Index: 444311 (C4 (Web Text))

Max Activating Token Index: 86

Text #15

Max Range: 0.5317. Min Range: -0.5317

Max Act: 0.3787. Min Act: -0.0000

Data Index: 1251792 (C4 (Web Text))

Max Activating Token Index: 294

Text #16

Max Range: 0.5317. Min Range: -0.5317

Max Act: 0.3417. Min Act: -0.0000

Data Index: 517549 (C4 (Web Text))

Max Activating Token Index: 693

Text #17

Max Range: 0.5317. Min Range: -0.5317

Max Act: 0.3572. Min Act: -0.0000

Data Index: 1017566 (C4 (Web Text))

Max Activating Token Index: 922

Text #18

Max Range: 0.5317. Min Range: -0.5317

Max Act: 0.4139. Min Act: -0.0000

Data Index: 1073864 (C4 (Web Text))

Max Activating Token Index: 1009

Text #19

Max Range: 0.5317. Min Range: -0.5317

Max Act: 0.3558. Min Act: -0.0000

Data Index: 598302 (C4 (Web Text))

Max Activating Token Index: 633