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

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

Neuron 2969 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: 0.0161. Min Range: -0.0161

Max Act: 0.0161. Min Act: -0.0002

Data Index: 436552 (C4 (Web Text))

Max Activating Token Index: 164

Text #1

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0141. Min Act: -0.0002

Data Index: 1082906 (C4 (Web Text))

Max Activating Token Index: 40

Text #2

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0138. Min Act: -0.0002

Data Index: 1077829 (C4 (Web Text))

Max Activating Token Index: 10

Text #3

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0128. Min Act: -0.0002

Data Index: 329838 (C4 (Web Text))

Max Activating Token Index: 871

Text #4

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0128. Min Act: -0.0002

Data Index: 469040 (C4 (Web Text))

Max Activating Token Index: 773

Text #5

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0128. Min Act: -0.0002

Data Index: 923170 (C4 (Web Text))

Max Activating Token Index: 17

Text #6

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0127. Min Act: -0.0002

Data Index: 66489 (C4 (Web Text))

Max Activating Token Index: 57

Text #7

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0125. Min Act: -0.0002

Data Index: 181925 (C4 (Web Text))

Max Activating Token Index: 104

Text #8

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0124. Min Act: -0.0002

Data Index: 279387 (C4 (Web Text))

Max Activating Token Index: 556

Text #9

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0123. Min Act: -0.0002

Data Index: 468360 (C4 (Web Text))

Max Activating Token Index: 148

Text #10

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0123. Min Act: -0.0002

Data Index: 583866 (C4 (Web Text))

Max Activating Token Index: 31

Text #11

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0123. Min Act: -0.0002

Data Index: 1286057 (C4 (Web Text))

Max Activating Token Index: 140

Text #12

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0125. Min Act: -0.0002

Data Index: 1039918 (C4 (Web Text))

Max Activating Token Index: 222

Text #13

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0122. Min Act: -0.0002

Data Index: 219946 (C4 (Web Text))

Max Activating Token Index: 307

Text #14

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0122. Min Act: -0.0002

Data Index: 143570 (C4 (Web Text))

Max Activating Token Index: 4

Text #15

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0122. Min Act: -0.0002

Data Index: 1212259 (C4 (Web Text))

Max Activating Token Index: 551

Text #16

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0122. Min Act: -0.0002

Data Index: 1293575 (C4 (Web Text))

Max Activating Token Index: 39

Text #17

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0121. Min Act: -0.0002

Data Index: 1347237 (C4 (Web Text))

Max Activating Token Index: 98

Text #18

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0118. Min Act: -0.0002

Data Index: 881914 (C4 (Web Text))

Max Activating Token Index: 126

Text #19

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0120. Min Act: -0.0002

Data Index: 562197 (C4 (Web Text))

Max Activating Token Index: 98