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

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

Neuron 2671 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7218. Min Range: -1.7218

Max Act: 1.7218. Min Act: -0.0000

Data Index: 939806 (C4 (Web Text))

Max Activating Token Index: 906

Text #1

Max Range: 1.7218. Min Range: -1.7218

Max Act: 0.9477. Min Act: -0.0000

Data Index: 1215578 (C4 (Web Text))

Max Activating Token Index: 994

Text #2

Max Range: 1.7218. Min Range: -1.7218

Max Act: 0.9156. Min Act: -0.0000

Data Index: 486076 (C4 (Web Text))

Max Activating Token Index: 634

Text #3

Max Range: 1.7218. Min Range: -1.7218

Max Act: 0.8971. Min Act: -0.0000

Data Index: 1351961 (C4 (Web Text))

Max Activating Token Index: 55

Text #4

Max Range: 1.7218. Min Range: -1.7218

Max Act: 0.8719. Min Act: -0.0000

Data Index: 225102 (C4 (Web Text))

Max Activating Token Index: 394

Text #5

Max Range: 1.7218. Min Range: -1.7218

Max Act: 0.8689. Min Act: -0.0000

Data Index: 778038 (C4 (Web Text))

Max Activating Token Index: 73

Text #6

Max Range: 1.7218. Min Range: -1.7218

Max Act: 0.8873. Min Act: -0.0000

Data Index: 419438 (C4 (Web Text))

Max Activating Token Index: 529

Text #7

Max Range: 1.7218. Min Range: -1.7218

Max Act: 0.8266. Min Act: -0.0000

Data Index: 102686 (C4 (Web Text))

Max Activating Token Index: 180

Text #8

Max Range: 1.7218. Min Range: -1.7218

Max Act: 0.8524. Min Act: -0.0000

Data Index: 839547 (C4 (Web Text))

Max Activating Token Index: 613

Text #9

Max Range: 1.7218. Min Range: -1.7218

Max Act: 0.8367. Min Act: -0.0000

Data Index: 873458 (C4 (Web Text))

Max Activating Token Index: 934

Text #10

Max Range: 1.7218. Min Range: -1.7218

Max Act: 0.8566. Min Act: -0.0000

Data Index: 670588 (C4 (Web Text))

Max Activating Token Index: 12

Text #11

Max Range: 1.7218. Min Range: -1.7218

Max Act: 0.7991. Min Act: -0.0000

Data Index: 397786 (C4 (Web Text))

Max Activating Token Index: 206

Text #12

Max Range: 1.7218. Min Range: -1.7218

Max Act: 0.8430. Min Act: -0.0000

Data Index: 61249 (C4 (Web Text))

Max Activating Token Index: 282

Text #13

Max Range: 1.7218. Min Range: -1.7218

Max Act: 0.8189. Min Act: -0.0000

Data Index: 963591 (C4 (Web Text))

Max Activating Token Index: 444

Text #14

Max Range: 1.7218. Min Range: -1.7218

Max Act: 0.8293. Min Act: -0.0000

Data Index: 254348 (C4 (Web Text))

Max Activating Token Index: 878

Text #15

Max Range: 1.7218. Min Range: -1.7218

Max Act: 0.7936. Min Act: -0.0000

Data Index: 305708 (C4 (Web Text))

Max Activating Token Index: 8

Text #16

Max Range: 1.7218. Min Range: -1.7218

Max Act: 0.7795. Min Act: -0.0000

Data Index: 742327 (C4 (Web Text))

Max Activating Token Index: 733

Text #17

Max Range: 1.7218. Min Range: -1.7218

Max Act: 0.8027. Min Act: -0.0000

Data Index: 149837 (C4 (Web Text))

Max Activating Token Index: 75

Text #18

Max Range: 1.7218. Min Range: -1.7218

Max Act: 0.7676. Min Act: -0.0000

Data Index: 1125947 (C4 (Web Text))

Max Activating Token Index: 607

Text #19

Max Range: 1.7218. Min Range: -1.7218

Max Act: 0.8158. Min Act: -0.0000

Data Index: 882197 (C4 (Web Text))

Max Activating Token Index: 896