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

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

Neuron 3990 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0048. Min Act: -0.0003

Data Index: 1180614 (C4 (Web Text))

Max Activating Token Index: 1

Text #1

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0048. Min Act: -0.0003

Data Index: 851367 (C4 (Web Text))

Max Activating Token Index: 1

Text #2

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0048. Min Act: -0.0002

Data Index: 727231 (C4 (Web Text))

Max Activating Token Index: 1

Text #3

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0048. Min Act: -0.0003

Data Index: 828995 (C4 (Web Text))

Max Activating Token Index: 1

Text #4

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0046. Min Act: -0.0003

Data Index: 1107766 (C4 (Web Text))

Max Activating Token Index: 654

Text #5

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0046. Min Act: -0.0003

Data Index: 697381 (C4 (Web Text))

Max Activating Token Index: 365

Text #6

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0046. Min Act: -0.0003

Data Index: 1278847 (C4 (Web Text))

Max Activating Token Index: 692

Text #7

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0045. Min Act: -0.0003

Data Index: 321767 (C4 (Web Text))

Max Activating Token Index: 4

Text #8

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0045. Min Act: -0.0003

Data Index: 547401 (C4 (Web Text))

Max Activating Token Index: 569

Text #9

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0044. Min Act: -0.0003

Data Index: 14314 (C4 (Web Text))

Max Activating Token Index: 2

Text #10

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0045. Min Act: -0.0003

Data Index: 332476 (C4 (Web Text))

Max Activating Token Index: 806

Text #11

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0044. Min Act: -0.0003

Data Index: 761927 (C4 (Web Text))

Max Activating Token Index: 270

Text #12

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0044. Min Act: -0.0003

Data Index: 830568 (C4 (Web Text))

Max Activating Token Index: 667

Text #13

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0044. Min Act: -0.0003

Data Index: 593842 (C4 (Web Text))

Max Activating Token Index: 289

Text #14

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0044. Min Act: -0.0003

Data Index: 922572 (C4 (Web Text))

Max Activating Token Index: 157

Text #15

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0043. Min Act: -0.0003

Data Index: 1011032 (C4 (Web Text))

Max Activating Token Index: 60

Text #16

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0043. Min Act: -0.0003

Data Index: 377997 (C4 (Web Text))

Max Activating Token Index: 805

Text #17

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0043. Min Act: -0.0003

Data Index: 128720 (C4 (Web Text))

Max Activating Token Index: 767

Text #18

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0043. Min Act: -0.0003

Data Index: 888480 (C4 (Web Text))

Max Activating Token Index: 629

Text #19

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0043. Min Act: -0.0003

Data Index: 91147 (C4 (Web Text))

Max Activating Token Index: 212