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

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

Neuron 619 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: 0.0088. Min Range: -0.0088

Max Act: 0.0088. Min Act: -0.0003

Data Index: 1145979 (C4 (Web Text))

Max Activating Token Index: 296

Text #1

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0081. Min Act: -0.0003

Data Index: 978489 (C4 (Web Text))

Max Activating Token Index: 976

Text #2

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0076. Min Act: -0.0003

Data Index: 892280 (C4 (Web Text))

Max Activating Token Index: 583

Text #3

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0077. Min Act: -0.0003

Data Index: 788137 (C4 (Web Text))

Max Activating Token Index: 722

Text #4

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0065. Min Act: -0.0003

Data Index: 1194966 (C4 (Web Text))

Max Activating Token Index: 801

Text #5

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0071. Min Act: -0.0003

Data Index: 283519 (C4 (Web Text))

Max Activating Token Index: 989

Text #6

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0079. Min Act: -0.0003

Data Index: 1225588 (C4 (Web Text))

Max Activating Token Index: 344

Text #7

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0066. Min Act: -0.0003

Data Index: 541488 (C4 (Web Text))

Max Activating Token Index: 147

Text #8

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0067. Min Act: -0.0004

Data Index: 578460 (C4 (Web Text))

Max Activating Token Index: 416

Text #9

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0065. Min Act: -0.0003

Data Index: 1016866 (C4 (Web Text))

Max Activating Token Index: 363

Text #10

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0062. Min Act: -0.0003

Data Index: 309070 (C4 (Web Text))

Max Activating Token Index: 799

Text #11

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0069. Min Act: -0.0003

Data Index: 110529 (C4 (Web Text))

Max Activating Token Index: 657

Text #12

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0064. Min Act: -0.0003

Data Index: 1052946 (C4 (Web Text))

Max Activating Token Index: 213

Text #13

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0065. Min Act: -0.0003

Data Index: 209676 (C4 (Web Text))

Max Activating Token Index: 74

Text #14

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0064. Min Act: -0.0003

Data Index: 498345 (C4 (Web Text))

Max Activating Token Index: 362

Text #15

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0062. Min Act: -0.0003

Data Index: 919249 (C4 (Web Text))

Max Activating Token Index: 476

Text #16

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0064. Min Act: -0.0003

Data Index: 537411 (C4 (Web Text))

Max Activating Token Index: 717

Text #17

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0060. Min Act: -0.0003

Data Index: 112831 (C4 (Web Text))

Max Activating Token Index: 925

Text #18

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0060. Min Act: -0.0003

Data Index: 1097638 (C4 (Web Text))

Max Activating Token Index: 420

Text #19

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0062. Min Act: -0.0003

Data Index: 225371 (C4 (Web Text))

Max Activating Token Index: 889