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

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

Neuron 1890 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0108. Min Act: -0.0006

Data Index: 385294 (C4 (Web Text))

Max Activating Token Index: 838

Text #1

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0100. Min Act: -0.0006

Data Index: 1334874 (C4 (Web Text))

Max Activating Token Index: 794

Text #2

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0090. Min Act: -0.0005

Data Index: 331748 (C4 (Web Text))

Max Activating Token Index: 972

Text #3

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0091. Min Act: -0.0006

Data Index: 193203 (C4 (Web Text))

Max Activating Token Index: 740

Text #4

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0091. Min Act: -0.0006

Data Index: 1065845 (C4 (Web Text))

Max Activating Token Index: 974

Text #5

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0088. Min Act: -0.0006

Data Index: 216435 (C4 (Web Text))

Max Activating Token Index: 723

Text #6

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0089. Min Act: -0.0006

Data Index: 1081245 (C4 (Web Text))

Max Activating Token Index: 262

Text #7

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0087. Min Act: -0.0005

Data Index: 864153 (C4 (Web Text))

Max Activating Token Index: 617

Text #8

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0085. Min Act: -0.0006

Data Index: 991502 (C4 (Web Text))

Max Activating Token Index: 768

Text #9

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0082. Min Act: -0.0006

Data Index: 1302993 (C4 (Web Text))

Max Activating Token Index: 916

Text #10

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0082. Min Act: -0.0005

Data Index: 621663 (C4 (Web Text))

Max Activating Token Index: 540

Text #11

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0083. Min Act: -0.0006

Data Index: 1562536 (Python Code)

Max Activating Token Index: 899

Text #12

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0084. Min Act: -0.0006

Data Index: 163568 (C4 (Web Text))

Max Activating Token Index: 751

Text #13

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0082. Min Act: -0.0006

Data Index: 1597573 (Python Code)

Max Activating Token Index: 1023

Text #14

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0082. Min Act: -0.0005

Data Index: 216790 (C4 (Web Text))

Max Activating Token Index: 887

Text #15

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0082. Min Act: -0.0006

Data Index: 96013 (C4 (Web Text))

Max Activating Token Index: 771

Text #16

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0084. Min Act: -0.0005

Data Index: 746120 (C4 (Web Text))

Max Activating Token Index: 904

Text #17

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0080. Min Act: -0.0006

Data Index: 935537 (C4 (Web Text))

Max Activating Token Index: 953

Text #18

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0082. Min Act: -0.0006

Data Index: 1044325 (C4 (Web Text))

Max Activating Token Index: 639

Text #19

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0080. Min Act: -0.0005

Data Index: 600406 (C4 (Web Text))

Max Activating Token Index: 492