Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 939 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0126. Min Act: -0.0003

Data Index: 756738 (C4 (Web Text))

Max Activating Token Index: 602

Text #1

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0115. Min Act: -0.0003

Data Index: 13706 (C4 (Web Text))

Max Activating Token Index: 539

Text #2

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0116. Min Act: -0.0003

Data Index: 683669 (C4 (Web Text))

Max Activating Token Index: 69

Text #3

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0115. Min Act: -0.0003

Data Index: 1330953 (C4 (Web Text))

Max Activating Token Index: 144

Text #4

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0112. Min Act: -0.0004

Data Index: 494923 (C4 (Web Text))

Max Activating Token Index: 1017

Text #5

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0108. Min Act: -0.0003

Data Index: 911045 (C4 (Web Text))

Max Activating Token Index: 81

Text #6

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0110. Min Act: -0.0004

Data Index: 1084775 (C4 (Web Text))

Max Activating Token Index: 269

Text #7

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0109. Min Act: -0.0004

Data Index: 939383 (C4 (Web Text))

Max Activating Token Index: 160

Text #8

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0109. Min Act: -0.0004

Data Index: 1347452 (C4 (Web Text))

Max Activating Token Index: 31

Text #9

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0106. Min Act: -0.0004

Data Index: 580426 (C4 (Web Text))

Max Activating Token Index: 895

Text #10

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0108. Min Act: -0.0003

Data Index: 906368 (C4 (Web Text))

Max Activating Token Index: 440

Text #11

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0104. Min Act: -0.0003

Data Index: 1211555 (C4 (Web Text))

Max Activating Token Index: 335

Text #12

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0107. Min Act: -0.0003

Data Index: 1071897 (C4 (Web Text))

Max Activating Token Index: 865

Text #13

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0106. Min Act: -0.0003

Data Index: 260205 (C4 (Web Text))

Max Activating Token Index: 73

Text #14

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0106. Min Act: -0.0003

Data Index: 1393303 (Python Code)

Max Activating Token Index: 862

Text #15

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0104. Min Act: -0.0004

Data Index: 162484 (C4 (Web Text))

Max Activating Token Index: 399

Text #16

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0106. Min Act: -0.0003

Data Index: 673685 (C4 (Web Text))

Max Activating Token Index: 933

Text #17

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0104. Min Act: -0.0003

Data Index: 1234735 (C4 (Web Text))

Max Activating Token Index: 1014

Text #18

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0103. Min Act: -0.0003

Data Index: 687243 (C4 (Web Text))

Max Activating Token Index: 70

Text #19

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0104. Min Act: -0.0004

Data Index: 760185 (C4 (Web Text))

Max Activating Token Index: 716