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

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

Neuron 3008 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: 1.8615. Min Range: -1.8615

Max Act: 1.8615. Min Act: -0.0000

Data Index: 19239 (C4 (Web Text))

Max Activating Token Index: 11

Text #1

Max Range: 1.8615. Min Range: -1.8615

Max Act: 1.6572. Min Act: -0.0000

Data Index: 1150258 (C4 (Web Text))

Max Activating Token Index: 437

Text #2

Max Range: 1.8615. Min Range: -1.8615

Max Act: 1.5994. Min Act: -0.0001

Data Index: 658664 (C4 (Web Text))

Max Activating Token Index: 2

Text #3

Max Range: 1.8615. Min Range: -1.8615

Max Act: 1.6331. Min Act: -0.0001

Data Index: 511081 (C4 (Web Text))

Max Activating Token Index: 560

Text #4

Max Range: 1.8615. Min Range: -1.8615

Max Act: 1.6160. Min Act: -0.0000

Data Index: 12570 (C4 (Web Text))

Max Activating Token Index: 83

Text #5

Max Range: 1.8615. Min Range: -1.8615

Max Act: 1.6308. Min Act: -0.0000

Data Index: 1351847 (C4 (Web Text))

Max Activating Token Index: 591

Text #6

Max Range: 1.8615. Min Range: -1.8615

Max Act: 1.4852. Min Act: -0.0000

Data Index: 115166 (C4 (Web Text))

Max Activating Token Index: 98

Text #7

Max Range: 1.8615. Min Range: -1.8615

Max Act: 1.5650. Min Act: -0.0000

Data Index: 190887 (C4 (Web Text))

Max Activating Token Index: 90

Text #8

Max Range: 1.8615. Min Range: -1.8615

Max Act: 1.4612. Min Act: -0.0001

Data Index: 426212 (C4 (Web Text))

Max Activating Token Index: 110

Text #9

Max Range: 1.8615. Min Range: -1.8615

Max Act: 1.3838. Min Act: -0.0000

Data Index: 571314 (C4 (Web Text))

Max Activating Token Index: 298

Text #10

Max Range: 1.8615. Min Range: -1.8615

Max Act: 1.4528. Min Act: -0.0000

Data Index: 1309900 (C4 (Web Text))

Max Activating Token Index: 246

Text #11

Max Range: 1.8615. Min Range: -1.8615

Max Act: 1.4082. Min Act: -0.0000

Data Index: 427490 (C4 (Web Text))

Max Activating Token Index: 66

Text #12

Max Range: 1.8615. Min Range: -1.8615

Max Act: 1.3628. Min Act: -0.0000

Data Index: 1113960 (C4 (Web Text))

Max Activating Token Index: 197

Text #13

Max Range: 1.8615. Min Range: -1.8615

Max Act: 1.3842. Min Act: -0.0000

Data Index: 734735 (C4 (Web Text))

Max Activating Token Index: 305

Text #14

Max Range: 1.8615. Min Range: -1.8615

Max Act: 1.4624. Min Act: -0.0000

Data Index: 1275155 (C4 (Web Text))

Max Activating Token Index: 94

Text #15

Max Range: 1.8615. Min Range: -1.8615

Max Act: 1.3066. Min Act: -0.0001

Data Index: 1094936 (C4 (Web Text))

Max Activating Token Index: 156

Text #16

Max Range: 1.8615. Min Range: -1.8615

Max Act: 1.3012. Min Act: -0.0000

Data Index: 146209 (C4 (Web Text))

Max Activating Token Index: 283

Text #17

Max Range: 1.8615. Min Range: -1.8615

Max Act: 1.3305. Min Act: -0.0000

Data Index: 944902 (C4 (Web Text))

Max Activating Token Index: 955

Text #18

Max Range: 1.8615. Min Range: -1.8615

Max Act: 1.2603. Min Act: -0.0000

Data Index: 848452 (C4 (Web Text))

Max Activating Token Index: 502

Text #19

Max Range: 1.8615. Min Range: -1.8615

Max Act: 1.2165. Min Act: -0.0000

Data Index: 921006 (C4 (Web Text))

Max Activating Token Index: 746