Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3716 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.8081. Min Range: -0.8081

Max Act: 0.7220. Min Act: -0.0001

Data Index: 171675 (C4 (Web Text))

Max Activating Token Index: 33

Text #1

Max Range: 0.8081. Min Range: -0.8081

Max Act: 0.8081. Min Act: -0.0001

Data Index: 338215 (C4 (Web Text))

Max Activating Token Index: 818

Text #2

Max Range: 0.8081. Min Range: -0.8081

Max Act: 0.6566. Min Act: -0.0002

Data Index: 340923 (C4 (Web Text))

Max Activating Token Index: 911

Text #3

Max Range: 0.8081. Min Range: -0.8081

Max Act: 0.7091. Min Act: -0.0001

Data Index: 1164774 (C4 (Web Text))

Max Activating Token Index: 769

Text #4

Max Range: 0.8081. Min Range: -0.8081

Max Act: 0.6515. Min Act: -0.0001

Data Index: 125275 (C4 (Web Text))

Max Activating Token Index: 59

Text #5

Max Range: 0.8081. Min Range: -0.8081

Max Act: 0.6313. Min Act: -0.0001

Data Index: 604408 (C4 (Web Text))

Max Activating Token Index: 601

Text #6

Max Range: 0.8081. Min Range: -0.8081

Max Act: 0.6887. Min Act: -0.0001

Data Index: 596701 (C4 (Web Text))

Max Activating Token Index: 533

Text #7

Max Range: 0.8081. Min Range: -0.8081

Max Act: 0.6107. Min Act: -0.0001

Data Index: 962113 (C4 (Web Text))

Max Activating Token Index: 628

Text #8

Max Range: 0.8081. Min Range: -0.8081

Max Act: 0.6800. Min Act: -0.0001

Data Index: 1233354 (C4 (Web Text))

Max Activating Token Index: 677

Text #9

Max Range: 0.8081. Min Range: -0.8081

Max Act: 0.6507. Min Act: -0.0001

Data Index: 759991 (C4 (Web Text))

Max Activating Token Index: 1003

Text #10

Max Range: 0.8081. Min Range: -0.8081

Max Act: 0.5117. Min Act: -0.0001

Data Index: 641008 (C4 (Web Text))

Max Activating Token Index: 994

Text #11

Max Range: 0.8081. Min Range: -0.8081

Max Act: 0.6204. Min Act: -0.0001

Data Index: 1152941 (C4 (Web Text))

Max Activating Token Index: 303

Text #12

Max Range: 0.8081. Min Range: -0.8081

Max Act: 0.5869. Min Act: -0.0001

Data Index: 622558 (C4 (Web Text))

Max Activating Token Index: 243

Text #13

Max Range: 0.8081. Min Range: -0.8081

Max Act: 0.6410. Min Act: -0.0002

Data Index: 374214 (C4 (Web Text))

Max Activating Token Index: 104

Text #14

Max Range: 0.8081. Min Range: -0.8081

Max Act: 0.5793. Min Act: -0.0001

Data Index: 692156 (C4 (Web Text))

Max Activating Token Index: 815

Text #15

Max Range: 0.8081. Min Range: -0.8081

Max Act: 0.6367. Min Act: -0.0001

Data Index: 1050014 (C4 (Web Text))

Max Activating Token Index: 579

Text #16

Max Range: 0.8081. Min Range: -0.8081

Max Act: 0.5930. Min Act: -0.0001

Data Index: 641582 (C4 (Web Text))

Max Activating Token Index: 548

Text #17

Max Range: 0.8081. Min Range: -0.8081

Max Act: 0.6730. Min Act: -0.0001

Data Index: 734074 (C4 (Web Text))

Max Activating Token Index: 735

Text #18

Max Range: 0.8081. Min Range: -0.8081

Max Act: 0.6054. Min Act: -0.0001

Data Index: 1078415 (C4 (Web Text))

Max Activating Token Index: 138

Text #19

Max Range: 0.8081. Min Range: -0.8081

Max Act: 0.6498. Min Act: -0.0001

Data Index: 977513 (C4 (Web Text))

Max Activating Token Index: 530