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

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

Neuron 3498 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0777. Min Range: -2.0777

Max Act: 2.0777. Min Act: -0.0000

Data Index: 1117256 (C4 (Web Text))

Max Activating Token Index: 17

Text #1

Max Range: 2.0777. Min Range: -2.0777

Max Act: 1.8665. Min Act: -0.0000

Data Index: 453056 (C4 (Web Text))

Max Activating Token Index: 14

Text #2

Max Range: 2.0777. Min Range: -2.0777

Max Act: 1.5255. Min Act: 0.0002

Data Index: 716248 (C4 (Web Text))

Max Activating Token Index: 3

Text #3

Max Range: 2.0777. Min Range: -2.0777

Max Act: 1.3760. Min Act: -0.0000

Data Index: 146147 (C4 (Web Text))

Max Activating Token Index: 23

Text #4

Max Range: 2.0777. Min Range: -2.0777

Max Act: 1.4396. Min Act: 0.0004

Data Index: 591640 (C4 (Web Text))

Max Activating Token Index: 18

Text #5

Max Range: 2.0777. Min Range: -2.0777

Max Act: 1.4296. Min Act: -0.0000

Data Index: 1177136 (C4 (Web Text))

Max Activating Token Index: 5

Text #6

Max Range: 2.0777. Min Range: -2.0777

Max Act: 1.4230. Min Act: -0.0000

Data Index: 988545 (C4 (Web Text))

Max Activating Token Index: 5

Text #7

Max Range: 2.0777. Min Range: -2.0777

Max Act: 1.4089. Min Act: -0.0000

Data Index: 364334 (C4 (Web Text))

Max Activating Token Index: 28

Text #8

Max Range: 2.0777. Min Range: -2.0777

Max Act: 1.4111. Min Act: -0.0000

Data Index: 786053 (C4 (Web Text))

Max Activating Token Index: 145

Text #9

Max Range: 2.0777. Min Range: -2.0777

Max Act: 1.3107. Min Act: -0.0000

Data Index: 1019920 (C4 (Web Text))

Max Activating Token Index: 14

Text #10

Max Range: 2.0777. Min Range: -2.0777

Max Act: 1.3674. Min Act: 0.0001

Data Index: 1014820 (C4 (Web Text))

Max Activating Token Index: 11

Text #11

Max Range: 2.0777. Min Range: -2.0777

Max Act: 1.3644. Min Act: 0.0002

Data Index: 511777 (C4 (Web Text))

Max Activating Token Index: 20

Text #12

Max Range: 2.0777. Min Range: -2.0777

Max Act: 1.2890. Min Act: -0.0000

Data Index: 975060 (C4 (Web Text))

Max Activating Token Index: 59

Text #13

Max Range: 2.0777. Min Range: -2.0777

Max Act: 1.3681. Min Act: 0.0000

Data Index: 1291828 (C4 (Web Text))

Max Activating Token Index: 11

Text #14

Max Range: 2.0777. Min Range: -2.0777

Max Act: 1.2716. Min Act: -0.0000

Data Index: 360798 (C4 (Web Text))

Max Activating Token Index: 8

Text #15

Max Range: 2.0777. Min Range: -2.0777

Max Act: 1.3530. Min Act: -0.0000

Data Index: 141623 (C4 (Web Text))

Max Activating Token Index: 9

Text #16

Max Range: 2.0777. Min Range: -2.0777

Max Act: 1.4259. Min Act: -0.0000

Data Index: 14886 (C4 (Web Text))

Max Activating Token Index: 8

Text #17

Max Range: 2.0777. Min Range: -2.0777

Max Act: 1.4177. Min Act: -0.0000

Data Index: 774898 (C4 (Web Text))

Max Activating Token Index: 6

Text #18

Max Range: 2.0777. Min Range: -2.0777

Max Act: 1.2400. Min Act: 0.0000

Data Index: 290872 (C4 (Web Text))

Max Activating Token Index: 15

Text #19

Max Range: 2.0777. Min Range: -2.0777

Max Act: 1.2986. Min Act: -0.0000

Data Index: 579927 (C4 (Web Text))

Max Activating Token Index: 11