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

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

Neuron 1731 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: 0.0134. Min Range: -0.0134

Max Act: 0.0132. Min Act: -0.0002

Data Index: 784914 (C4 (Web Text))

Max Activating Token Index: 1010

Text #1

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0134. Min Act: -0.0002

Data Index: 631766 (C4 (Web Text))

Max Activating Token Index: 397

Text #2

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0133. Min Act: -0.0002

Data Index: 1206615 (C4 (Web Text))

Max Activating Token Index: 1021

Text #3

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0130. Min Act: -0.0002

Data Index: 135906 (C4 (Web Text))

Max Activating Token Index: 229

Text #4

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0127. Min Act: -0.0002

Data Index: 594872 (C4 (Web Text))

Max Activating Token Index: 140

Text #5

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0128. Min Act: -0.0002

Data Index: 837041 (C4 (Web Text))

Max Activating Token Index: 27

Text #6

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0128. Min Act: -0.0002

Data Index: 686336 (C4 (Web Text))

Max Activating Token Index: 747

Text #7

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0127. Min Act: -0.0002

Data Index: 96493 (C4 (Web Text))

Max Activating Token Index: 142

Text #8

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0127. Min Act: -0.0002

Data Index: 1339185 (C4 (Web Text))

Max Activating Token Index: 33

Text #9

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0127. Min Act: -0.0002

Data Index: 584358 (C4 (Web Text))

Max Activating Token Index: 1002

Text #10

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0127. Min Act: -0.0002

Data Index: 952195 (C4 (Web Text))

Max Activating Token Index: 1010

Text #11

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0127. Min Act: -0.0002

Data Index: 924374 (C4 (Web Text))

Max Activating Token Index: 132

Text #12

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0127. Min Act: -0.0002

Data Index: 1176588 (C4 (Web Text))

Max Activating Token Index: 886

Text #13

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0126. Min Act: -0.0002

Data Index: 88596 (C4 (Web Text))

Max Activating Token Index: 56

Text #14

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0126. Min Act: -0.0002

Data Index: 235261 (C4 (Web Text))

Max Activating Token Index: 10

Text #15

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0126. Min Act: -0.0002

Data Index: 349392 (C4 (Web Text))

Max Activating Token Index: 1021

Text #16

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0126. Min Act: -0.0002

Data Index: 976078 (C4 (Web Text))

Max Activating Token Index: 832

Text #17

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0125. Min Act: -0.0002

Data Index: 720035 (C4 (Web Text))

Max Activating Token Index: 736

Text #18

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0125. Min Act: -0.0002

Data Index: 235254 (C4 (Web Text))

Max Activating Token Index: 35

Text #19

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0125. Min Act: -0.0002

Data Index: 674048 (C4 (Web Text))

Max Activating Token Index: 988