Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3942 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0064. Min Act: -0.0002

Data Index: 807305 (C4 (Web Text))

Max Activating Token Index: 42

Text #1

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0063. Min Act: -0.0002

Data Index: 1339085 (C4 (Web Text))

Max Activating Token Index: 21

Text #2

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0060. Min Act: -0.0002

Data Index: 1172978 (C4 (Web Text))

Max Activating Token Index: 50

Text #3

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0059. Min Act: -0.0002

Data Index: 619689 (C4 (Web Text))

Max Activating Token Index: 39

Text #4

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0059. Min Act: -0.0002

Data Index: 918518 (C4 (Web Text))

Max Activating Token Index: 48

Text #5

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0059. Min Act: -0.0002

Data Index: 530382 (C4 (Web Text))

Max Activating Token Index: 113

Text #6

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0059. Min Act: -0.0002

Data Index: 119003 (C4 (Web Text))

Max Activating Token Index: 20

Text #7

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0059. Min Act: -0.0002

Data Index: 709281 (C4 (Web Text))

Max Activating Token Index: 373

Text #8

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0059. Min Act: -0.0002

Data Index: 407283 (C4 (Web Text))

Max Activating Token Index: 342

Text #9

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0059. Min Act: -0.0002

Data Index: 90126 (C4 (Web Text))

Max Activating Token Index: 455

Text #10

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0059. Min Act: -0.0002

Data Index: 1120613 (C4 (Web Text))

Max Activating Token Index: 589

Text #11

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0059. Min Act: -0.0002

Data Index: 341449 (C4 (Web Text))

Max Activating Token Index: 102

Text #12

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0058. Min Act: -0.0002

Data Index: 120520 (C4 (Web Text))

Max Activating Token Index: 208

Text #13

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0058. Min Act: -0.0002

Data Index: 444498 (C4 (Web Text))

Max Activating Token Index: 73

Text #14

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0058. Min Act: -0.0002

Data Index: 1048158 (C4 (Web Text))

Max Activating Token Index: 442

Text #15

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0059. Min Act: -0.0002

Data Index: 670903 (C4 (Web Text))

Max Activating Token Index: 61

Text #16

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0057. Min Act: -0.0002

Data Index: 1208486 (C4 (Web Text))

Max Activating Token Index: 641

Text #17

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0057. Min Act: -0.0002

Data Index: 568063 (C4 (Web Text))

Max Activating Token Index: 404

Text #18

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0058. Min Act: -0.0002

Data Index: 436439 (C4 (Web Text))

Max Activating Token Index: 90

Text #19

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0057. Min Act: -0.0002

Data Index: 961888 (C4 (Web Text))

Max Activating Token Index: 562