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

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

Neuron 4641 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0135. Min Act: -0.0002

Data Index: 750738 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0093. Min Act: -0.0002

Data Index: 106665 (C4 (Web Text))

Max Activating Token Index: 149

Text #2

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0088. Min Act: -0.0002

Data Index: 1063682 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0088. Min Act: -0.0002

Data Index: 491106 (C4 (Web Text))

Max Activating Token Index: 893

Text #4

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0094. Min Act: -0.0002

Data Index: 686301 (C4 (Web Text))

Max Activating Token Index: 498

Text #5

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0127. Min Act: -0.0002

Data Index: 743086 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0087. Min Act: -0.0002

Data Index: 1247925 (C4 (Web Text))

Max Activating Token Index: 525

Text #7

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0056. Min Act: -0.0002

Data Index: 757165 (C4 (Web Text))

Max Activating Token Index: 647

Text #8

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0088. Min Act: -0.0002

Data Index: 630063 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0097. Min Act: -0.0002

Data Index: 253118 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0096. Min Act: -0.0002

Data Index: 1311332 (C4 (Web Text))

Max Activating Token Index: 986

Text #11

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0084. Min Act: -0.0002

Data Index: 881425 (C4 (Web Text))

Max Activating Token Index: 39

Text #12

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0079. Min Act: -0.0002

Data Index: 433636 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0083. Min Act: -0.0002

Data Index: 1301211 (C4 (Web Text))

Max Activating Token Index: 989

Text #14

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0090. Min Act: -0.0002

Data Index: 49694 (C4 (Web Text))

Max Activating Token Index: 409

Text #15

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0072. Min Act: -0.0002

Data Index: 402182 (C4 (Web Text))

Max Activating Token Index: 169

Text #16

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0085. Min Act: -0.0002

Data Index: 848322 (C4 (Web Text))

Max Activating Token Index: 80

Text #17

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0083. Min Act: -0.0002

Data Index: 1456030 (Python Code)

Max Activating Token Index: 47

Text #18

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0089. Min Act: -0.0002

Data Index: 573252 (C4 (Web Text))

Max Activating Token Index: 275

Text #19

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0066. Min Act: -0.0002

Data Index: 6853 (C4 (Web Text))

Max Activating Token Index: 1023