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

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

Neuron 286 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1257. Min Range: -0.1257

Max Act: 0.1233. Min Act: -0.0000

Data Index: 365567 (C4 (Web Text))

Max Activating Token Index: 808

Text #1

Max Range: 0.1257. Min Range: -0.1257

Max Act: 0.1257. Min Act: -0.0000

Data Index: 760396 (C4 (Web Text))

Max Activating Token Index: 512

Text #2

Max Range: 0.1257. Min Range: -0.1257

Max Act: 0.1075. Min Act: -0.0000

Data Index: 1193728 (C4 (Web Text))

Max Activating Token Index: 107

Text #3

Max Range: 0.1257. Min Range: -0.1257

Max Act: 0.1244. Min Act: -0.0001

Data Index: 176992 (C4 (Web Text))

Max Activating Token Index: 960

Text #4

Max Range: 0.1257. Min Range: -0.1257

Max Act: 0.1076. Min Act: -0.0000

Data Index: 1226630 (C4 (Web Text))

Max Activating Token Index: 717

Text #5

Max Range: 0.1257. Min Range: -0.1257

Max Act: 0.1042. Min Act: -0.0000

Data Index: 232692 (C4 (Web Text))

Max Activating Token Index: 413

Text #6

Max Range: 0.1257. Min Range: -0.1257

Max Act: 0.1097. Min Act: -0.0000

Data Index: 419033 (C4 (Web Text))

Max Activating Token Index: 555

Text #7

Max Range: 0.1257. Min Range: -0.1257

Max Act: 0.1080. Min Act: -0.0000

Data Index: 588102 (C4 (Web Text))

Max Activating Token Index: 303

Text #8

Max Range: 0.1257. Min Range: -0.1257

Max Act: 0.1038. Min Act: -0.0000

Data Index: 77181 (C4 (Web Text))

Max Activating Token Index: 965

Text #9

Max Range: 0.1257. Min Range: -0.1257

Max Act: 0.1028. Min Act: -0.0000

Data Index: 525960 (C4 (Web Text))

Max Activating Token Index: 102

Text #10

Max Range: 0.1257. Min Range: -0.1257

Max Act: 0.1097. Min Act: -0.0000

Data Index: 564881 (C4 (Web Text))

Max Activating Token Index: 900

Text #11

Max Range: 0.1257. Min Range: -0.1257

Max Act: 0.1123. Min Act: -0.0000

Data Index: 254102 (C4 (Web Text))

Max Activating Token Index: 947

Text #12

Max Range: 0.1257. Min Range: -0.1257

Max Act: 0.1063. Min Act: -0.0000

Data Index: 524022 (C4 (Web Text))

Max Activating Token Index: 716

Text #13

Max Range: 0.1257. Min Range: -0.1257

Max Act: 0.1010. Min Act: -0.0000

Data Index: 95155 (C4 (Web Text))

Max Activating Token Index: 399

Text #14

Max Range: 0.1257. Min Range: -0.1257

Max Act: 0.1010. Min Act: -0.0001

Data Index: 311607 (C4 (Web Text))

Max Activating Token Index: 729

Text #15

Max Range: 0.1257. Min Range: -0.1257

Max Act: 0.1002. Min Act: -0.0001

Data Index: 589678 (C4 (Web Text))

Max Activating Token Index: 475

Text #16

Max Range: 0.1257. Min Range: -0.1257

Max Act: 0.1035. Min Act: -0.0000

Data Index: 1132061 (C4 (Web Text))

Max Activating Token Index: 233

Text #17

Max Range: 0.1257. Min Range: -0.1257

Max Act: 0.1031. Min Act: -0.0000

Data Index: 1155594 (C4 (Web Text))

Max Activating Token Index: 38

Text #18

Max Range: 0.1257. Min Range: -0.1257

Max Act: 0.0990. Min Act: -0.0000

Data Index: 980864 (C4 (Web Text))

Max Activating Token Index: 590

Text #19

Max Range: 0.1257. Min Range: -0.1257

Max Act: 0.0991. Min Act: -0.0000

Data Index: 429774 (C4 (Web Text))

Max Activating Token Index: 131