Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3087 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.6142. Min Range: -1.6142

Max Act: 1.6142. Min Act: -0.0001

Data Index: 274670 (C4 (Web Text))

Max Activating Token Index: 925

Text #1

Max Range: 1.6142. Min Range: -1.6142

Max Act: 1.3733. Min Act: -0.0002

Data Index: 938013 (C4 (Web Text))

Max Activating Token Index: 633

Text #2

Max Range: 1.6142. Min Range: -1.6142

Max Act: 1.3811. Min Act: -0.0002

Data Index: 770709 (C4 (Web Text))

Max Activating Token Index: 440

Text #3

Max Range: 1.6142. Min Range: -1.6142

Max Act: 1.4572. Min Act: -0.0002

Data Index: 68352 (C4 (Web Text))

Max Activating Token Index: 719

Text #4

Max Range: 1.6142. Min Range: -1.6142

Max Act: 1.3767. Min Act: -0.0002

Data Index: 221997 (C4 (Web Text))

Max Activating Token Index: 483

Text #5

Max Range: 1.6142. Min Range: -1.6142

Max Act: 1.3462. Min Act: -0.0002

Data Index: 392537 (C4 (Web Text))

Max Activating Token Index: 872

Text #6

Max Range: 1.6142. Min Range: -1.6142

Max Act: 1.4015. Min Act: -0.0001

Data Index: 201349 (C4 (Web Text))

Max Activating Token Index: 751

Text #7

Max Range: 1.6142. Min Range: -1.6142

Max Act: 1.3125. Min Act: -0.0002

Data Index: 521917 (C4 (Web Text))

Max Activating Token Index: 392

Text #8

Max Range: 1.6142. Min Range: -1.6142

Max Act: 1.2567. Min Act: -0.0002

Data Index: 726449 (C4 (Web Text))

Max Activating Token Index: 985

Text #9

Max Range: 1.6142. Min Range: -1.6142

Max Act: 1.2652. Min Act: -0.0002

Data Index: 251921 (C4 (Web Text))

Max Activating Token Index: 412

Text #10

Max Range: 1.6142. Min Range: -1.6142

Max Act: 1.3043. Min Act: -0.0002

Data Index: 1102137 (C4 (Web Text))

Max Activating Token Index: 68

Text #11

Max Range: 1.6142. Min Range: -1.6142

Max Act: 1.1257. Min Act: -0.0001

Data Index: 871020 (C4 (Web Text))

Max Activating Token Index: 374

Text #12

Max Range: 1.6142. Min Range: -1.6142

Max Act: 1.1474. Min Act: -0.0002

Data Index: 1195397 (C4 (Web Text))

Max Activating Token Index: 503

Text #13

Max Range: 1.6142. Min Range: -1.6142

Max Act: 1.2170. Min Act: -0.0002

Data Index: 463181 (C4 (Web Text))

Max Activating Token Index: 838

Text #14

Max Range: 1.6142. Min Range: -1.6142

Max Act: 1.2586. Min Act: -0.0002

Data Index: 1302751 (C4 (Web Text))

Max Activating Token Index: 126

Text #15

Max Range: 1.6142. Min Range: -1.6142

Max Act: 1.1754. Min Act: -0.0001

Data Index: 800382 (C4 (Web Text))

Max Activating Token Index: 43

Text #16

Max Range: 1.6142. Min Range: -1.6142

Max Act: 1.0994. Min Act: -0.0002

Data Index: 1041258 (C4 (Web Text))

Max Activating Token Index: 734

Text #17

Max Range: 1.6142. Min Range: -1.6142

Max Act: 1.1014. Min Act: -0.0002

Data Index: 461059 (C4 (Web Text))

Max Activating Token Index: 675

Text #18

Max Range: 1.6142. Min Range: -1.6142

Max Act: 1.1229. Min Act: -0.0001

Data Index: 163670 (C4 (Web Text))

Max Activating Token Index: 892

Text #19

Max Range: 1.6142. Min Range: -1.6142

Max Act: 1.0937. Min Act: -0.0001

Data Index: 612593 (C4 (Web Text))

Max Activating Token Index: 501