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

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

Neuron 1787 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0125. Min Act: -0.0003

Data Index: 809086 (C4 (Web Text))

Max Activating Token Index: 571

Text #1

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0123. Min Act: -0.0003

Data Index: 512285 (C4 (Web Text))

Max Activating Token Index: 459

Text #2

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0101. Min Act: -0.0003

Data Index: 152354 (C4 (Web Text))

Max Activating Token Index: 720

Text #3

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0099. Min Act: -0.0003

Data Index: 1244642 (C4 (Web Text))

Max Activating Token Index: 881

Text #4

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0095. Min Act: -0.0003

Data Index: 809942 (C4 (Web Text))

Max Activating Token Index: 147

Text #5

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0095. Min Act: -0.0003

Data Index: 806196 (C4 (Web Text))

Max Activating Token Index: 31

Text #6

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0087. Min Act: -0.0003

Data Index: 393030 (C4 (Web Text))

Max Activating Token Index: 83

Text #7

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0096. Min Act: -0.0003

Data Index: 740 (C4 (Web Text))

Max Activating Token Index: 291

Text #8

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0091. Min Act: -0.0003

Data Index: 391317 (C4 (Web Text))

Max Activating Token Index: 220

Text #9

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0089. Min Act: -0.0003

Data Index: 330555 (C4 (Web Text))

Max Activating Token Index: 991

Text #10

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0091. Min Act: -0.0003

Data Index: 884443 (C4 (Web Text))

Max Activating Token Index: 380

Text #11

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0086. Min Act: -0.0003

Data Index: 1334822 (C4 (Web Text))

Max Activating Token Index: 932

Text #12

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0093. Min Act: -0.0003

Data Index: 365950 (C4 (Web Text))

Max Activating Token Index: 905

Text #13

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0087. Min Act: -0.0003

Data Index: 353361 (C4 (Web Text))

Max Activating Token Index: 879

Text #14

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0083. Min Act: -0.0003

Data Index: 711482 (C4 (Web Text))

Max Activating Token Index: 943

Text #15

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0091. Min Act: -0.0003

Data Index: 177709 (C4 (Web Text))

Max Activating Token Index: 117

Text #16

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0087. Min Act: -0.0004

Data Index: 908510 (C4 (Web Text))

Max Activating Token Index: 310

Text #17

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0088. Min Act: -0.0003

Data Index: 575184 (C4 (Web Text))

Max Activating Token Index: 65

Text #18

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0083. Min Act: -0.0003

Data Index: 426261 (C4 (Web Text))

Max Activating Token Index: 986

Text #19

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0087. Min Act: -0.0003

Data Index: 50862 (C4 (Web Text))

Max Activating Token Index: 288