Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 262 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5524. Min Range: -0.5524

Max Act: 0.5524. Min Act: -0.0001

Data Index: 57077 (C4 (Web Text))

Max Activating Token Index: 37

Text #1

Max Range: 0.5524. Min Range: -0.5524

Max Act: 0.5493. Min Act: -0.0002

Data Index: 756911 (C4 (Web Text))

Max Activating Token Index: 36

Text #2

Max Range: 0.5524. Min Range: -0.5524

Max Act: 0.5521. Min Act: -0.0002

Data Index: 1100689 (C4 (Web Text))

Max Activating Token Index: 40

Text #3

Max Range: 0.5524. Min Range: -0.5524

Max Act: 0.5396. Min Act: -0.0002

Data Index: 198274 (C4 (Web Text))

Max Activating Token Index: 38

Text #4

Max Range: 0.5524. Min Range: -0.5524

Max Act: 0.5206. Min Act: -0.0002

Data Index: 72582 (C4 (Web Text))

Max Activating Token Index: 40

Text #5

Max Range: 0.5524. Min Range: -0.5524

Max Act: 0.5142. Min Act: -0.0001

Data Index: 1186479 (C4 (Web Text))

Max Activating Token Index: 41

Text #6

Max Range: 0.5524. Min Range: -0.5524

Max Act: 0.4943. Min Act: -0.0002

Data Index: 358311 (C4 (Web Text))

Max Activating Token Index: 37

Text #7

Max Range: 0.5524. Min Range: -0.5524

Max Act: 0.5075. Min Act: -0.0002

Data Index: 391003 (C4 (Web Text))

Max Activating Token Index: 42

Text #8

Max Range: 0.5524. Min Range: -0.5524

Max Act: 0.5051. Min Act: -0.0002

Data Index: 853572 (C4 (Web Text))

Max Activating Token Index: 36

Text #9

Max Range: 0.5524. Min Range: -0.5524

Max Act: 0.5078. Min Act: -0.0002

Data Index: 42072 (C4 (Web Text))

Max Activating Token Index: 41

Text #10

Max Range: 0.5524. Min Range: -0.5524

Max Act: 0.5222. Min Act: -0.0001

Data Index: 414865 (C4 (Web Text))

Max Activating Token Index: 52

Text #11

Max Range: 0.5524. Min Range: -0.5524

Max Act: 0.5219. Min Act: -0.0002

Data Index: 302656 (C4 (Web Text))

Max Activating Token Index: 56

Text #12

Max Range: 0.5524. Min Range: -0.5524

Max Act: 0.5058. Min Act: -0.0001

Data Index: 203162 (C4 (Web Text))

Max Activating Token Index: 58

Text #13

Max Range: 0.5524. Min Range: -0.5524

Max Act: 0.4860. Min Act: -0.0001

Data Index: 302964 (C4 (Web Text))

Max Activating Token Index: 50

Text #14

Max Range: 0.5524. Min Range: -0.5524

Max Act: 0.4980. Min Act: -0.0002

Data Index: 439469 (C4 (Web Text))

Max Activating Token Index: 55

Text #15

Max Range: 0.5524. Min Range: -0.5524

Max Act: 0.4794. Min Act: -0.0002

Data Index: 167968 (C4 (Web Text))

Max Activating Token Index: 43

Text #16

Max Range: 0.5524. Min Range: -0.5524

Max Act: 0.4813. Min Act: -0.0001

Data Index: 397176 (C4 (Web Text))

Max Activating Token Index: 44

Text #17

Max Range: 0.5524. Min Range: -0.5524

Max Act: 0.4938. Min Act: -0.0001

Data Index: 649767 (C4 (Web Text))

Max Activating Token Index: 33

Text #18

Max Range: 0.5524. Min Range: -0.5524

Max Act: 0.4801. Min Act: -0.0002

Data Index: 27384 (C4 (Web Text))

Max Activating Token Index: 60

Text #19

Max Range: 0.5524. Min Range: -0.5524

Max Act: 0.4901. Min Act: -0.0002

Data Index: 71913 (C4 (Web Text))

Max Activating Token Index: 33