Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1612 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0107. Min Act: -0.0005

Data Index: 890374 (C4 (Web Text))

Max Activating Token Index: 678

Text #1

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0106. Min Act: -0.0005

Data Index: 1106746 (C4 (Web Text))

Max Activating Token Index: 138

Text #2

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0098. Min Act: -0.0006

Data Index: 693522 (C4 (Web Text))

Max Activating Token Index: 199

Text #3

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0095. Min Act: -0.0006

Data Index: 554003 (C4 (Web Text))

Max Activating Token Index: 763

Text #4

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0095. Min Act: -0.0006

Data Index: 874862 (C4 (Web Text))

Max Activating Token Index: 863

Text #5

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0092. Min Act: -0.0006

Data Index: 91029 (C4 (Web Text))

Max Activating Token Index: 928

Text #6

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0089. Min Act: -0.0006

Data Index: 150699 (C4 (Web Text))

Max Activating Token Index: 394

Text #7

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0087. Min Act: -0.0006

Data Index: 193480 (C4 (Web Text))

Max Activating Token Index: 552

Text #8

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0086. Min Act: -0.0006

Data Index: 78657 (C4 (Web Text))

Max Activating Token Index: 880

Text #9

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0086. Min Act: -0.0006

Data Index: 210958 (C4 (Web Text))

Max Activating Token Index: 808

Text #10

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0086. Min Act: -0.0006

Data Index: 504284 (C4 (Web Text))

Max Activating Token Index: 120

Text #11

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0086. Min Act: -0.0006

Data Index: 200592 (C4 (Web Text))

Max Activating Token Index: 689

Text #12

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0085. Min Act: -0.0007

Data Index: 285534 (C4 (Web Text))

Max Activating Token Index: 230

Text #13

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0084. Min Act: -0.0006

Data Index: 769768 (C4 (Web Text))

Max Activating Token Index: 848

Text #14

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0082. Min Act: -0.0006

Data Index: 656275 (C4 (Web Text))

Max Activating Token Index: 90

Text #15

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0082. Min Act: -0.0006

Data Index: 489043 (C4 (Web Text))

Max Activating Token Index: 740

Text #16

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0083. Min Act: -0.0006

Data Index: 190556 (C4 (Web Text))

Max Activating Token Index: 437

Text #17

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0083. Min Act: -0.0006

Data Index: 369071 (C4 (Web Text))

Max Activating Token Index: 113

Text #18

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0081. Min Act: -0.0006

Data Index: 234360 (C4 (Web Text))

Max Activating Token Index: 347

Text #19

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0081. Min Act: -0.0006

Data Index: 568881 (C4 (Web Text))

Max Activating Token Index: 322