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

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

Neuron 1398 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0049. Min Range: -2.0049

Max Act: 2.0049. Min Act: -0.0000

Data Index: 889554 (C4 (Web Text))

Max Activating Token Index: 900

Text #1

Max Range: 2.0049. Min Range: -2.0049

Max Act: 1.7363. Min Act: -0.0000

Data Index: 1303204 (C4 (Web Text))

Max Activating Token Index: 504

Text #2

Max Range: 2.0049. Min Range: -2.0049

Max Act: 1.7274. Min Act: -0.0000

Data Index: 361775 (C4 (Web Text))

Max Activating Token Index: 772

Text #3

Max Range: 2.0049. Min Range: -2.0049

Max Act: 1.8293. Min Act: -0.0000

Data Index: 850184 (C4 (Web Text))

Max Activating Token Index: 526

Text #4

Max Range: 2.0049. Min Range: -2.0049

Max Act: 1.8840. Min Act: -0.0000

Data Index: 910110 (C4 (Web Text))

Max Activating Token Index: 132

Text #5

Max Range: 2.0049. Min Range: -2.0049

Max Act: 1.7361. Min Act: -0.0000

Data Index: 911623 (C4 (Web Text))

Max Activating Token Index: 444

Text #6

Max Range: 2.0049. Min Range: -2.0049

Max Act: 1.7191. Min Act: -0.0000

Data Index: 266849 (C4 (Web Text))

Max Activating Token Index: 73

Text #7

Max Range: 2.0049. Min Range: -2.0049

Max Act: 1.6132. Min Act: -0.0000

Data Index: 630383 (C4 (Web Text))

Max Activating Token Index: 940

Text #8

Max Range: 2.0049. Min Range: -2.0049

Max Act: 1.8237. Min Act: -0.0000

Data Index: 1095233 (C4 (Web Text))

Max Activating Token Index: 316

Text #9

Max Range: 2.0049. Min Range: -2.0049

Max Act: 1.6286. Min Act: -0.0000

Data Index: 308751 (C4 (Web Text))

Max Activating Token Index: 507

Text #10

Max Range: 2.0049. Min Range: -2.0049

Max Act: 1.6041. Min Act: -0.0000

Data Index: 924352 (C4 (Web Text))

Max Activating Token Index: 233

Text #11

Max Range: 2.0049. Min Range: -2.0049

Max Act: 1.4907. Min Act: -0.0000

Data Index: 729065 (C4 (Web Text))

Max Activating Token Index: 39

Text #12

Max Range: 2.0049. Min Range: -2.0049

Max Act: 1.4982. Min Act: -0.0000

Data Index: 750501 (C4 (Web Text))

Max Activating Token Index: 509

Text #13

Max Range: 2.0049. Min Range: -2.0049

Max Act: 1.5544. Min Act: -0.0000

Data Index: 480045 (C4 (Web Text))

Max Activating Token Index: 192

Text #14

Max Range: 2.0049. Min Range: -2.0049

Max Act: 1.5538. Min Act: -0.0000

Data Index: 48333 (C4 (Web Text))

Max Activating Token Index: 495

Text #15

Max Range: 2.0049. Min Range: -2.0049

Max Act: 1.5393. Min Act: -0.0000

Data Index: 886917 (C4 (Web Text))

Max Activating Token Index: 448

Text #16

Max Range: 2.0049. Min Range: -2.0049

Max Act: 1.6348. Min Act: -0.0000

Data Index: 330124 (C4 (Web Text))

Max Activating Token Index: 122

Text #17

Max Range: 2.0049. Min Range: -2.0049

Max Act: 1.5431. Min Act: -0.0000

Data Index: 701676 (C4 (Web Text))

Max Activating Token Index: 32

Text #18

Max Range: 2.0049. Min Range: -2.0049

Max Act: 1.5833. Min Act: -0.0000

Data Index: 62843 (C4 (Web Text))

Max Activating Token Index: 345

Text #19

Max Range: 2.0049. Min Range: -2.0049

Max Act: 1.4955. Min Act: -0.0000

Data Index: 1303869 (C4 (Web Text))

Max Activating Token Index: 79