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

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

Neuron 2222 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0140. Min Act: -0.0003

Data Index: 784356 (C4 (Web Text))

Max Activating Token Index: 31

Text #1

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0134. Min Act: -0.0002

Data Index: 1558499 (Python Code)

Max Activating Token Index: 10

Text #2

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0133. Min Act: -0.0003

Data Index: 1044989 (C4 (Web Text))

Max Activating Token Index: 180

Text #3

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0132. Min Act: -0.0002

Data Index: 1394612 (Python Code)

Max Activating Token Index: 303

Text #4

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0134. Min Act: -0.0002

Data Index: 1520421 (Python Code)

Max Activating Token Index: 722

Text #5

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0130. Min Act: -0.0003

Data Index: 776660 (C4 (Web Text))

Max Activating Token Index: 5

Text #6

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0129. Min Act: -0.0003

Data Index: 669020 (C4 (Web Text))

Max Activating Token Index: 926

Text #7

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0128. Min Act: -0.0003

Data Index: 1345950 (C4 (Web Text))

Max Activating Token Index: 20

Text #8

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0128. Min Act: -0.0002

Data Index: 1593807 (Python Code)

Max Activating Token Index: 21

Text #9

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0125. Min Act: -0.0003

Data Index: 537369 (C4 (Web Text))

Max Activating Token Index: 201

Text #10

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0125. Min Act: -0.0003

Data Index: 841105 (C4 (Web Text))

Max Activating Token Index: 549

Text #11

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0127. Min Act: -0.0003

Data Index: 969949 (C4 (Web Text))

Max Activating Token Index: 92

Text #12

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0127. Min Act: -0.0003

Data Index: 838387 (C4 (Web Text))

Max Activating Token Index: 647

Text #13

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0124. Min Act: -0.0003

Data Index: 187950 (C4 (Web Text))

Max Activating Token Index: 189

Text #14

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0124. Min Act: -0.0003

Data Index: 486853 (C4 (Web Text))

Max Activating Token Index: 5

Text #15

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0122. Min Act: -0.0002

Data Index: 1437153 (Python Code)

Max Activating Token Index: 195

Text #16

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0122. Min Act: -0.0003

Data Index: 1231701 (C4 (Web Text))

Max Activating Token Index: 152

Text #17

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0122. Min Act: -0.0003

Data Index: 30008 (C4 (Web Text))

Max Activating Token Index: 88

Text #18

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0121. Min Act: -0.0003

Data Index: 519600 (C4 (Web Text))

Max Activating Token Index: 657

Text #19

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0123. Min Act: -0.0002

Data Index: 1158625 (C4 (Web Text))

Max Activating Token Index: 303