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

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

Neuron 1018 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5128. Min Range: -2.5128

Max Act: 2.5086. Min Act: -0.0000

Data Index: 45275 (C4 (Web Text))

Max Activating Token Index: 446

Text #1

Max Range: 2.5128. Min Range: -2.5128

Max Act: 2.5128. Min Act: -0.0000

Data Index: 228031 (C4 (Web Text))

Max Activating Token Index: 681

Text #2

Max Range: 2.5128. Min Range: -2.5128

Max Act: 2.4742. Min Act: -0.0000

Data Index: 1353989 (C4 (Web Text))

Max Activating Token Index: 460

Text #3

Max Range: 2.5128. Min Range: -2.5128

Max Act: 2.3450. Min Act: -0.0000

Data Index: 617579 (C4 (Web Text))

Max Activating Token Index: 534

Text #4

Max Range: 2.5128. Min Range: -2.5128

Max Act: 2.3571. Min Act: -0.0000

Data Index: 1322951 (C4 (Web Text))

Max Activating Token Index: 417

Text #5

Max Range: 2.5128. Min Range: -2.5128

Max Act: 2.4621. Min Act: -0.0000

Data Index: 155399 (C4 (Web Text))

Max Activating Token Index: 54

Text #6

Max Range: 2.5128. Min Range: -2.5128

Max Act: 2.3163. Min Act: -0.0000

Data Index: 1160132 (C4 (Web Text))

Max Activating Token Index: 86

Text #7

Max Range: 2.5128. Min Range: -2.5128

Max Act: 2.4295. Min Act: -0.0000

Data Index: 832369 (C4 (Web Text))

Max Activating Token Index: 788

Text #8

Max Range: 2.5128. Min Range: -2.5128

Max Act: 2.5044. Min Act: -0.0000

Data Index: 28198 (C4 (Web Text))

Max Activating Token Index: 462

Text #9

Max Range: 2.5128. Min Range: -2.5128

Max Act: 2.3559. Min Act: -0.0000

Data Index: 1030054 (C4 (Web Text))

Max Activating Token Index: 647

Text #10

Max Range: 2.5128. Min Range: -2.5128

Max Act: 2.3034. Min Act: -0.0000

Data Index: 1063359 (C4 (Web Text))

Max Activating Token Index: 920

Text #11

Max Range: 2.5128. Min Range: -2.5128

Max Act: 2.1850. Min Act: -0.0000

Data Index: 1030199 (C4 (Web Text))

Max Activating Token Index: 163

Text #12

Max Range: 2.5128. Min Range: -2.5128

Max Act: 2.2697. Min Act: -0.0000

Data Index: 344589 (C4 (Web Text))

Max Activating Token Index: 231

Text #13

Max Range: 2.5128. Min Range: -2.5128

Max Act: 2.2687. Min Act: -0.0000

Data Index: 1093895 (C4 (Web Text))

Max Activating Token Index: 318

Text #14

Max Range: 2.5128. Min Range: -2.5128

Max Act: 2.1562. Min Act: -0.0000

Data Index: 1068441 (C4 (Web Text))

Max Activating Token Index: 338

Text #15

Max Range: 2.5128. Min Range: -2.5128

Max Act: 2.2384. Min Act: -0.0000

Data Index: 854745 (C4 (Web Text))

Max Activating Token Index: 718

Text #16

Max Range: 2.5128. Min Range: -2.5128

Max Act: 2.1082. Min Act: -0.0000

Data Index: 174023 (C4 (Web Text))

Max Activating Token Index: 624

Text #17

Max Range: 2.5128. Min Range: -2.5128

Max Act: 2.1017. Min Act: -0.0000

Data Index: 1071101 (C4 (Web Text))

Max Activating Token Index: 353

Text #18

Max Range: 2.5128. Min Range: -2.5128

Max Act: 1.9773. Min Act: -0.0000

Data Index: 64788 (C4 (Web Text))

Max Activating Token Index: 244

Text #19

Max Range: 2.5128. Min Range: -2.5128

Max Act: 2.0373. Min Act: -0.0000

Data Index: 1005091 (C4 (Web Text))

Max Activating Token Index: 699