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

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

Neuron 744 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: 0.0106. Min Range: -0.0106

Max Act: 0.0106. Min Act: -0.0006

Data Index: 623732 (C4 (Web Text))

Max Activating Token Index: 310

Text #1

Max Range: 0.0106. Min Range: -0.0106

Max Act: 0.0103. Min Act: -0.0006

Data Index: 879747 (C4 (Web Text))

Max Activating Token Index: 726

Text #2

Max Range: 0.0106. Min Range: -0.0106

Max Act: 0.0100. Min Act: -0.0006

Data Index: 1028873 (C4 (Web Text))

Max Activating Token Index: 457

Text #3

Max Range: 0.0106. Min Range: -0.0106

Max Act: 0.0099. Min Act: -0.0006

Data Index: 679303 (C4 (Web Text))

Max Activating Token Index: 818

Text #4

Max Range: 0.0106. Min Range: -0.0106

Max Act: 0.0097. Min Act: -0.0006

Data Index: 865305 (C4 (Web Text))

Max Activating Token Index: 943

Text #5

Max Range: 0.0106. Min Range: -0.0106

Max Act: 0.0096. Min Act: -0.0006

Data Index: 1365512 (Python Code)

Max Activating Token Index: 573

Text #6

Max Range: 0.0106. Min Range: -0.0106

Max Act: 0.0098. Min Act: -0.0006

Data Index: 824427 (C4 (Web Text))

Max Activating Token Index: 414

Text #7

Max Range: 0.0106. Min Range: -0.0106

Max Act: 0.0096. Min Act: -0.0006

Data Index: 1086701 (C4 (Web Text))

Max Activating Token Index: 876

Text #8

Max Range: 0.0106. Min Range: -0.0106

Max Act: 0.0097. Min Act: -0.0006

Data Index: 1056322 (C4 (Web Text))

Max Activating Token Index: 153

Text #9

Max Range: 0.0106. Min Range: -0.0106

Max Act: 0.0097. Min Act: -0.0006

Data Index: 78341 (C4 (Web Text))

Max Activating Token Index: 642

Text #10

Max Range: 0.0106. Min Range: -0.0106

Max Act: 0.0095. Min Act: -0.0006

Data Index: 791151 (C4 (Web Text))

Max Activating Token Index: 919

Text #11

Max Range: 0.0106. Min Range: -0.0106

Max Act: 0.0095. Min Act: -0.0006

Data Index: 1554368 (Python Code)

Max Activating Token Index: 447

Text #12

Max Range: 0.0106. Min Range: -0.0106

Max Act: 0.0095. Min Act: -0.0005

Data Index: 611975 (C4 (Web Text))

Max Activating Token Index: 993

Text #13

Max Range: 0.0106. Min Range: -0.0106

Max Act: 0.0095. Min Act: -0.0006

Data Index: 714839 (C4 (Web Text))

Max Activating Token Index: 69

Text #14

Max Range: 0.0106. Min Range: -0.0106

Max Act: 0.0094. Min Act: -0.0006

Data Index: 1641883 (Python Code)

Max Activating Token Index: 604

Text #15

Max Range: 0.0106. Min Range: -0.0106

Max Act: 0.0095. Min Act: -0.0006

Data Index: 243236 (C4 (Web Text))

Max Activating Token Index: 784

Text #16

Max Range: 0.0106. Min Range: -0.0106

Max Act: 0.0093. Min Act: -0.0006

Data Index: 3621 (C4 (Web Text))

Max Activating Token Index: 701

Text #17

Max Range: 0.0106. Min Range: -0.0106

Max Act: 0.0093. Min Act: -0.0006

Data Index: 695365 (C4 (Web Text))

Max Activating Token Index: 107

Text #18

Max Range: 0.0106. Min Range: -0.0106

Max Act: 0.0092. Min Act: -0.0007

Data Index: 1291245 (C4 (Web Text))

Max Activating Token Index: 803

Text #19

Max Range: 0.0106. Min Range: -0.0106

Max Act: 0.0092. Min Act: -0.0006

Data Index: 250153 (C4 (Web Text))

Max Activating Token Index: 72