Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1401 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0070. Min Act: -0.0004

Data Index: 293398 (C4 (Web Text))

Max Activating Token Index: 510

Text #1

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0070. Min Act: -0.0004

Data Index: 1191907 (C4 (Web Text))

Max Activating Token Index: 811

Text #2

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0070. Min Act: -0.0004

Data Index: 1544731 (Python Code)

Max Activating Token Index: 836

Text #3

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0069. Min Act: -0.0004

Data Index: 1575716 (Python Code)

Max Activating Token Index: 78

Text #4

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0068. Min Act: -0.0004

Data Index: 1160769 (C4 (Web Text))

Max Activating Token Index: 983

Text #5

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0068. Min Act: -0.0004

Data Index: 1275921 (C4 (Web Text))

Max Activating Token Index: 699

Text #6

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0067. Min Act: -0.0004

Data Index: 473194 (C4 (Web Text))

Max Activating Token Index: 962

Text #7

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0067. Min Act: -0.0004

Data Index: 660196 (C4 (Web Text))

Max Activating Token Index: 650

Text #8

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0067. Min Act: -0.0004

Data Index: 594508 (C4 (Web Text))

Max Activating Token Index: 453

Text #9

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0067. Min Act: -0.0004

Data Index: 459609 (C4 (Web Text))

Max Activating Token Index: 681

Text #10

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0066. Min Act: -0.0003

Data Index: 1479920 (Python Code)

Max Activating Token Index: 796

Text #11

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0066. Min Act: -0.0004

Data Index: 275348 (C4 (Web Text))

Max Activating Token Index: 720

Text #12

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0066. Min Act: -0.0004

Data Index: 1066140 (C4 (Web Text))

Max Activating Token Index: 797

Text #13

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0066. Min Act: -0.0004

Data Index: 769961 (C4 (Web Text))

Max Activating Token Index: 888

Text #14

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0066. Min Act: -0.0004

Data Index: 1090874 (C4 (Web Text))

Max Activating Token Index: 933

Text #15

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0066. Min Act: -0.0004

Data Index: 1125830 (C4 (Web Text))

Max Activating Token Index: 447

Text #16

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0065. Min Act: -0.0003

Data Index: 1570988 (Python Code)

Max Activating Token Index: 938

Text #17

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0065. Min Act: -0.0004

Data Index: 892913 (C4 (Web Text))

Max Activating Token Index: 512

Text #18

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0065. Min Act: -0.0004

Data Index: 66714 (C4 (Web Text))

Max Activating Token Index: 873

Text #19

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0064. Min Act: -0.0004

Data Index: 1431147 (Python Code)

Max Activating Token Index: 684