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

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

Neuron 3539 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: 0.7944. Min Range: -0.7944

Max Act: 0.7601. Min Act: -0.0000

Data Index: 703051 (C4 (Web Text))

Max Activating Token Index: 683

Text #1

Max Range: 0.7944. Min Range: -0.7944

Max Act: 0.7563. Min Act: -0.0000

Data Index: 1308600 (C4 (Web Text))

Max Activating Token Index: 742

Text #2

Max Range: 0.7944. Min Range: -0.7944

Max Act: 0.7944. Min Act: -0.0000

Data Index: 1064970 (C4 (Web Text))

Max Activating Token Index: 65

Text #3

Max Range: 0.7944. Min Range: -0.7944

Max Act: 0.7290. Min Act: -0.0000

Data Index: 938458 (C4 (Web Text))

Max Activating Token Index: 958

Text #4

Max Range: 0.7944. Min Range: -0.7944

Max Act: 0.7402. Min Act: -0.0000

Data Index: 585919 (C4 (Web Text))

Max Activating Token Index: 21

Text #5

Max Range: 0.7944. Min Range: -0.7944

Max Act: 0.7064. Min Act: -0.0000

Data Index: 1379514 (Python Code)

Max Activating Token Index: 436

Text #6

Max Range: 0.7944. Min Range: -0.7944

Max Act: 0.7003. Min Act: -0.0000

Data Index: 1125995 (C4 (Web Text))

Max Activating Token Index: 572

Text #7

Max Range: 0.7944. Min Range: -0.7944

Max Act: 0.6324. Min Act: -0.0000

Data Index: 1332344 (C4 (Web Text))

Max Activating Token Index: 349

Text #8

Max Range: 0.7944. Min Range: -0.7944

Max Act: 0.6501. Min Act: -0.0000

Data Index: 243340 (C4 (Web Text))

Max Activating Token Index: 561

Text #9

Max Range: 0.7944. Min Range: -0.7944

Max Act: 0.6033. Min Act: -0.0000

Data Index: 163929 (C4 (Web Text))

Max Activating Token Index: 268

Text #10

Max Range: 0.7944. Min Range: -0.7944

Max Act: 0.7059. Min Act: -0.0000

Data Index: 1123558 (C4 (Web Text))

Max Activating Token Index: 138

Text #11

Max Range: 0.7944. Min Range: -0.7944

Max Act: 0.6381. Min Act: -0.0000

Data Index: 1251360 (C4 (Web Text))

Max Activating Token Index: 532

Text #12

Max Range: 0.7944. Min Range: -0.7944

Max Act: 0.6384. Min Act: -0.0000

Data Index: 110363 (C4 (Web Text))

Max Activating Token Index: 34

Text #13

Max Range: 0.7944. Min Range: -0.7944

Max Act: 0.6260. Min Act: -0.0000

Data Index: 631183 (C4 (Web Text))

Max Activating Token Index: 351

Text #14

Max Range: 0.7944. Min Range: -0.7944

Max Act: 0.5921. Min Act: -0.0000

Data Index: 898689 (C4 (Web Text))

Max Activating Token Index: 974

Text #15

Max Range: 0.7944. Min Range: -0.7944

Max Act: 0.6321. Min Act: -0.0000

Data Index: 776683 (C4 (Web Text))

Max Activating Token Index: 209

Text #16

Max Range: 0.7944. Min Range: -0.7944

Max Act: 0.6308. Min Act: -0.0000

Data Index: 1223800 (C4 (Web Text))

Max Activating Token Index: 921

Text #17

Max Range: 0.7944. Min Range: -0.7944

Max Act: 0.5698. Min Act: -0.0000

Data Index: 818854 (C4 (Web Text))

Max Activating Token Index: 263

Text #18

Max Range: 0.7944. Min Range: -0.7944

Max Act: 0.6070. Min Act: -0.0000

Data Index: 1043122 (C4 (Web Text))

Max Activating Token Index: 918

Text #19

Max Range: 0.7944. Min Range: -0.7944

Max Act: 0.5663. Min Act: -0.0000

Data Index: 438394 (C4 (Web Text))

Max Activating Token Index: 434