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

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

Neuron 2212 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0174. Min Range: -0.0174

Max Act: 0.0174. Min Act: -0.0001

Data Index: 800103 (C4 (Web Text))

Max Activating Token Index: 122

Text #1

Max Range: 0.0174. Min Range: -0.0174

Max Act: 0.0142. Min Act: -0.0001

Data Index: 1247812 (C4 (Web Text))

Max Activating Token Index: 136

Text #2

Max Range: 0.0174. Min Range: -0.0174

Max Act: 0.0146. Min Act: -0.0001

Data Index: 145765 (C4 (Web Text))

Max Activating Token Index: 85

Text #3

Max Range: 0.0174. Min Range: -0.0174

Max Act: 0.0142. Min Act: -0.0001

Data Index: 1243202 (C4 (Web Text))

Max Activating Token Index: 964

Text #4

Max Range: 0.0174. Min Range: -0.0174

Max Act: 0.0139. Min Act: -0.0001

Data Index: 37026 (C4 (Web Text))

Max Activating Token Index: 253

Text #5

Max Range: 0.0174. Min Range: -0.0174

Max Act: 0.0131. Min Act: -0.0001

Data Index: 745490 (C4 (Web Text))

Max Activating Token Index: 6

Text #6

Max Range: 0.0174. Min Range: -0.0174

Max Act: 0.0126. Min Act: -0.0001

Data Index: 1295631 (C4 (Web Text))

Max Activating Token Index: 679

Text #7

Max Range: 0.0174. Min Range: -0.0174

Max Act: 0.0131. Min Act: -0.0001

Data Index: 544552 (C4 (Web Text))

Max Activating Token Index: 80

Text #8

Max Range: 0.0174. Min Range: -0.0174

Max Act: 0.0128. Min Act: -0.0001

Data Index: 10562 (C4 (Web Text))

Max Activating Token Index: 143

Text #9

Max Range: 0.0174. Min Range: -0.0174

Max Act: 0.0127. Min Act: -0.0001

Data Index: 1535611 (Python Code)

Max Activating Token Index: 5

Text #10

Max Range: 0.0174. Min Range: -0.0174

Max Act: 0.0121. Min Act: -0.0001

Data Index: 85591 (C4 (Web Text))

Max Activating Token Index: 807

Text #11

Max Range: 0.0174. Min Range: -0.0174

Max Act: 0.0120. Min Act: -0.0001

Data Index: 191610 (C4 (Web Text))

Max Activating Token Index: 10

Text #12

Max Range: 0.0174. Min Range: -0.0174

Max Act: 0.0127. Min Act: -0.0001

Data Index: 398021 (C4 (Web Text))

Max Activating Token Index: 106

Text #13

Max Range: 0.0174. Min Range: -0.0174

Max Act: 0.0118. Min Act: -0.0001

Data Index: 523666 (C4 (Web Text))

Max Activating Token Index: 37

Text #14

Max Range: 0.0174. Min Range: -0.0174

Max Act: 0.0122. Min Act: -0.0001

Data Index: 316831 (C4 (Web Text))

Max Activating Token Index: 692

Text #15

Max Range: 0.0174. Min Range: -0.0174

Max Act: 0.0121. Min Act: -0.0001

Data Index: 909962 (C4 (Web Text))

Max Activating Token Index: 57

Text #16

Max Range: 0.0174. Min Range: -0.0174

Max Act: 0.0126. Min Act: -0.0001

Data Index: 407492 (C4 (Web Text))

Max Activating Token Index: 911

Text #17

Max Range: 0.0174. Min Range: -0.0174

Max Act: 0.0124. Min Act: -0.0001

Data Index: 217005 (C4 (Web Text))

Max Activating Token Index: 36

Text #18

Max Range: 0.0174. Min Range: -0.0174

Max Act: 0.0121. Min Act: -0.0001

Data Index: 879476 (C4 (Web Text))

Max Activating Token Index: 156

Text #19

Max Range: 0.0174. Min Range: -0.0174

Max Act: 0.0119. Min Act: -0.0001

Data Index: 935664 (C4 (Web Text))

Max Activating Token Index: 152