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

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

Neuron 375 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0068. Min Act: -0.0000

Data Index: 958233 (C4 (Web Text))

Max Activating Token Index: 589

Text #1

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0057. Min Act: -0.0000

Data Index: 1263256 (C4 (Web Text))

Max Activating Token Index: 324

Text #2

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0044. Min Act: -0.0000

Data Index: 1131809 (C4 (Web Text))

Max Activating Token Index: 220

Text #3

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0041. Min Act: -0.0000

Data Index: 848138 (C4 (Web Text))

Max Activating Token Index: 646

Text #4

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0042. Min Act: -0.0000

Data Index: 274906 (C4 (Web Text))

Max Activating Token Index: 549

Text #5

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0037. Min Act: -0.0000

Data Index: 1242979 (C4 (Web Text))

Max Activating Token Index: 947

Text #6

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0034. Min Act: -0.0000

Data Index: 483407 (C4 (Web Text))

Max Activating Token Index: 492

Text #7

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0031. Min Act: -0.0001

Data Index: 780543 (C4 (Web Text))

Max Activating Token Index: 456

Text #8

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0031. Min Act: -0.0000

Data Index: 1314531 (C4 (Web Text))

Max Activating Token Index: 108

Text #9

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0022. Min Act: -0.0001

Data Index: 743507 (C4 (Web Text))

Max Activating Token Index: 295

Text #10

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0030. Min Act: -0.0001

Data Index: 1005787 (C4 (Web Text))

Max Activating Token Index: 736

Text #11

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0013. Min Act: -0.0000

Data Index: 386995 (C4 (Web Text))

Max Activating Token Index: 534

Text #12

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0014. Min Act: -0.0000

Data Index: 1375210 (Python Code)

Max Activating Token Index: 111

Text #13

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0015. Min Act: -0.0000

Data Index: 847645 (C4 (Web Text))

Max Activating Token Index: 60

Text #14

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0012. Min Act: -0.0000

Data Index: 1189774 (C4 (Web Text))

Max Activating Token Index: 997

Text #15

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0012. Min Act: -0.0000

Data Index: 1460402 (Python Code)

Max Activating Token Index: 597

Text #16

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0009. Min Act: -0.0000

Data Index: 333452 (C4 (Web Text))

Max Activating Token Index: 147

Text #17

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0012. Min Act: -0.0000

Data Index: 670593 (C4 (Web Text))

Max Activating Token Index: 84

Text #18

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0011. Min Act: -0.0000

Data Index: 734213 (C4 (Web Text))

Max Activating Token Index: 31

Text #19

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0011. Min Act: -0.0000

Data Index: 536711 (C4 (Web Text))

Max Activating Token Index: 611