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

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

Neuron 371 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0074. Min Range: -0.0074

Max Act: 0.0074. Min Act: -0.0006

Data Index: 756762 (C4 (Web Text))

Max Activating Token Index: 896

Text #1

Max Range: 0.0074. Min Range: -0.0074

Max Act: 0.0072. Min Act: -0.0006

Data Index: 604788 (C4 (Web Text))

Max Activating Token Index: 877

Text #2

Max Range: 0.0074. Min Range: -0.0074

Max Act: 0.0071. Min Act: -0.0006

Data Index: 497044 (C4 (Web Text))

Max Activating Token Index: 998

Text #3

Max Range: 0.0074. Min Range: -0.0074

Max Act: 0.0074. Min Act: -0.0006

Data Index: 53752 (C4 (Web Text))

Max Activating Token Index: 681

Text #4

Max Range: 0.0074. Min Range: -0.0074

Max Act: 0.0071. Min Act: -0.0006

Data Index: 256813 (C4 (Web Text))

Max Activating Token Index: 11

Text #5

Max Range: 0.0074. Min Range: -0.0074

Max Act: 0.0069. Min Act: -0.0006

Data Index: 33292 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.0074. Min Range: -0.0074

Max Act: 0.0069. Min Act: -0.0006

Data Index: 752862 (C4 (Web Text))

Max Activating Token Index: 1012

Text #7

Max Range: 0.0074. Min Range: -0.0074

Max Act: 0.0069. Min Act: -0.0006

Data Index: 386011 (C4 (Web Text))

Max Activating Token Index: 95

Text #8

Max Range: 0.0074. Min Range: -0.0074

Max Act: 0.0067. Min Act: -0.0006

Data Index: 549512 (C4 (Web Text))

Max Activating Token Index: 721

Text #9

Max Range: 0.0074. Min Range: -0.0074

Max Act: 0.0069. Min Act: -0.0006

Data Index: 1301133 (C4 (Web Text))

Max Activating Token Index: 416

Text #10

Max Range: 0.0074. Min Range: -0.0074

Max Act: 0.0067. Min Act: -0.0006

Data Index: 296681 (C4 (Web Text))

Max Activating Token Index: 772

Text #11

Max Range: 0.0074. Min Range: -0.0074

Max Act: 0.0066. Min Act: -0.0006

Data Index: 706080 (C4 (Web Text))

Max Activating Token Index: 101

Text #12

Max Range: 0.0074. Min Range: -0.0074

Max Act: 0.0067. Min Act: -0.0006

Data Index: 879003 (C4 (Web Text))

Max Activating Token Index: 43

Text #13

Max Range: 0.0074. Min Range: -0.0074

Max Act: 0.0066. Min Act: -0.0006

Data Index: 870747 (C4 (Web Text))

Max Activating Token Index: 286

Text #14

Max Range: 0.0074. Min Range: -0.0074

Max Act: 0.0066. Min Act: -0.0006

Data Index: 1174945 (C4 (Web Text))

Max Activating Token Index: 993

Text #15

Max Range: 0.0074. Min Range: -0.0074

Max Act: 0.0065. Min Act: -0.0006

Data Index: 35234 (C4 (Web Text))

Max Activating Token Index: 635

Text #16

Max Range: 0.0074. Min Range: -0.0074

Max Act: 0.0066. Min Act: -0.0006

Data Index: 1149864 (C4 (Web Text))

Max Activating Token Index: 430

Text #17

Max Range: 0.0074. Min Range: -0.0074

Max Act: 0.0066. Min Act: -0.0006

Data Index: 146526 (C4 (Web Text))

Max Activating Token Index: 83

Text #18

Max Range: 0.0074. Min Range: -0.0074

Max Act: 0.0065. Min Act: -0.0006

Data Index: 710083 (C4 (Web Text))

Max Activating Token Index: 698

Text #19

Max Range: 0.0074. Min Range: -0.0074

Max Act: 0.0066. Min Act: -0.0006

Data Index: 541206 (C4 (Web Text))

Max Activating Token Index: 955