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

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

Neuron 1094 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: 1.0057. Min Range: -1.0057

Max Act: 1.0057. Min Act: -0.0001

Data Index: 1001535 (C4 (Web Text))

Max Activating Token Index: 148

Text #1

Max Range: 1.0057. Min Range: -1.0057

Max Act: 0.8970. Min Act: -0.0000

Data Index: 50667 (C4 (Web Text))

Max Activating Token Index: 148

Text #2

Max Range: 1.0057. Min Range: -1.0057

Max Act: 0.9129. Min Act: -0.0000

Data Index: 1287846 (C4 (Web Text))

Max Activating Token Index: 82

Text #3

Max Range: 1.0057. Min Range: -1.0057

Max Act: 0.8817. Min Act: -0.0000

Data Index: 178286 (C4 (Web Text))

Max Activating Token Index: 12

Text #4

Max Range: 1.0057. Min Range: -1.0057

Max Act: 0.9149. Min Act: -0.0000

Data Index: 501581 (C4 (Web Text))

Max Activating Token Index: 221

Text #5

Max Range: 1.0057. Min Range: -1.0057

Max Act: 0.9000. Min Act: -0.0000

Data Index: 527101 (C4 (Web Text))

Max Activating Token Index: 716

Text #6

Max Range: 1.0057. Min Range: -1.0057

Max Act: 0.8438. Min Act: -0.0000

Data Index: 601690 (C4 (Web Text))

Max Activating Token Index: 707

Text #7

Max Range: 1.0057. Min Range: -1.0057

Max Act: 0.8604. Min Act: -0.0001

Data Index: 1344859 (C4 (Web Text))

Max Activating Token Index: 397

Text #8

Max Range: 1.0057. Min Range: -1.0057

Max Act: 0.9072. Min Act: -0.0000

Data Index: 1038533 (C4 (Web Text))

Max Activating Token Index: 914

Text #9

Max Range: 1.0057. Min Range: -1.0057

Max Act: 0.8100. Min Act: -0.0000

Data Index: 745109 (C4 (Web Text))

Max Activating Token Index: 165

Text #10

Max Range: 1.0057. Min Range: -1.0057

Max Act: 0.7883. Min Act: -0.0000

Data Index: 498132 (C4 (Web Text))

Max Activating Token Index: 934

Text #11

Max Range: 1.0057. Min Range: -1.0057

Max Act: 0.8255. Min Act: -0.0000

Data Index: 1190388 (C4 (Web Text))

Max Activating Token Index: 464

Text #12

Max Range: 1.0057. Min Range: -1.0057

Max Act: 0.7841. Min Act: -0.0000

Data Index: 1235644 (C4 (Web Text))

Max Activating Token Index: 792

Text #13

Max Range: 1.0057. Min Range: -1.0057

Max Act: 0.8364. Min Act: -0.0000

Data Index: 274924 (C4 (Web Text))

Max Activating Token Index: 939

Text #14

Max Range: 1.0057. Min Range: -1.0057

Max Act: 0.8287. Min Act: -0.0000

Data Index: 538954 (C4 (Web Text))

Max Activating Token Index: 69

Text #15

Max Range: 1.0057. Min Range: -1.0057

Max Act: 0.7756. Min Act: -0.0000

Data Index: 1171955 (C4 (Web Text))

Max Activating Token Index: 60

Text #16

Max Range: 1.0057. Min Range: -1.0057

Max Act: 0.7784. Min Act: -0.0000

Data Index: 40153 (C4 (Web Text))

Max Activating Token Index: 536

Text #17

Max Range: 1.0057. Min Range: -1.0057

Max Act: 0.7796. Min Act: -0.0000

Data Index: 9207 (C4 (Web Text))

Max Activating Token Index: 96

Text #18

Max Range: 1.0057. Min Range: -1.0057

Max Act: 0.7780. Min Act: -0.0000

Data Index: 796690 (C4 (Web Text))

Max Activating Token Index: 99

Text #19

Max Range: 1.0057. Min Range: -1.0057

Max Act: 0.7522. Min Act: -0.0000

Data Index: 739071 (C4 (Web Text))

Max Activating Token Index: 264