Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 97 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0083. Min Act: -0.0005

Data Index: 1415772 (Python Code)

Max Activating Token Index: 244

Text #1

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0073. Min Act: -0.0005

Data Index: 1611479 (Python Code)

Max Activating Token Index: 609

Text #2

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0072. Min Act: -0.0005

Data Index: 1499550 (Python Code)

Max Activating Token Index: 448

Text #3

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0071. Min Act: -0.0005

Data Index: 1463365 (Python Code)

Max Activating Token Index: 889

Text #4

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0070. Min Act: -0.0006

Data Index: 301158 (C4 (Web Text))

Max Activating Token Index: 606

Text #5

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0069. Min Act: -0.0005

Data Index: 710261 (C4 (Web Text))

Max Activating Token Index: 781

Text #6

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0069. Min Act: -0.0006

Data Index: 1246115 (C4 (Web Text))

Max Activating Token Index: 653

Text #7

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0067. Min Act: -0.0005

Data Index: 1475207 (Python Code)

Max Activating Token Index: 781

Text #8

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0067. Min Act: -0.0005

Data Index: 1599748 (Python Code)

Max Activating Token Index: 1015

Text #9

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0066. Min Act: -0.0005

Data Index: 1611981 (Python Code)

Max Activating Token Index: 910

Text #10

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0066. Min Act: -0.0005

Data Index: 1462247 (Python Code)

Max Activating Token Index: 942

Text #11

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0066. Min Act: -0.0005

Data Index: 861878 (C4 (Web Text))

Max Activating Token Index: 485

Text #12

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0065. Min Act: -0.0005

Data Index: 364021 (C4 (Web Text))

Max Activating Token Index: 605

Text #13

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0064. Min Act: -0.0005

Data Index: 464803 (C4 (Web Text))

Max Activating Token Index: 506

Text #14

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0063. Min Act: -0.0005

Data Index: 790554 (C4 (Web Text))

Max Activating Token Index: 902

Text #15

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0062. Min Act: -0.0005

Data Index: 213914 (C4 (Web Text))

Max Activating Token Index: 385

Text #16

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0062. Min Act: -0.0005

Data Index: 1642365 (Python Code)

Max Activating Token Index: 880

Text #17

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0062. Min Act: -0.0005

Data Index: 1609621 (Python Code)

Max Activating Token Index: 243

Text #18

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0061. Min Act: -0.0005

Data Index: 267068 (C4 (Web Text))

Max Activating Token Index: 851

Text #19

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0060. Min Act: -0.0005

Data Index: 1370049 (Python Code)

Max Activating Token Index: 867