Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 6100 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.4766. Min Range: -3.4766

Max Act: 3.4766. Min Act: -0.0000

Data Index: 829440 (C4 (Web Text))

Max Activating Token Index: 446

Text #1

Max Range: 3.4766. Min Range: -3.4766

Max Act: 3.0306. Min Act: -0.0000

Data Index: 138680 (C4 (Web Text))

Max Activating Token Index: 724

Text #2

Max Range: 3.4766. Min Range: -3.4766

Max Act: 3.0424. Min Act: -0.0000

Data Index: 18361 (C4 (Web Text))

Max Activating Token Index: 318

Text #3

Max Range: 3.4766. Min Range: -3.4766

Max Act: 2.9048. Min Act: -0.0000

Data Index: 74952 (C4 (Web Text))

Max Activating Token Index: 826

Text #4

Max Range: 3.4766. Min Range: -3.4766

Max Act: 2.6634. Min Act: -0.0000

Data Index: 876773 (C4 (Web Text))

Max Activating Token Index: 1012

Text #5

Max Range: 3.4766. Min Range: -3.4766

Max Act: 2.7877. Min Act: -0.0000

Data Index: 1040900 (C4 (Web Text))

Max Activating Token Index: 433

Text #6

Max Range: 3.4766. Min Range: -3.4766

Max Act: 2.8030. Min Act: -0.0000

Data Index: 323259 (C4 (Web Text))

Max Activating Token Index: 818

Text #7

Max Range: 3.4766. Min Range: -3.4766

Max Act: 2.6257. Min Act: -0.0000

Data Index: 1009865 (C4 (Web Text))

Max Activating Token Index: 633

Text #8

Max Range: 3.4766. Min Range: -3.4766

Max Act: 2.6249. Min Act: -0.0000

Data Index: 634599 (C4 (Web Text))

Max Activating Token Index: 439

Text #9

Max Range: 3.4766. Min Range: -3.4766

Max Act: 2.6049. Min Act: -0.0000

Data Index: 309878 (C4 (Web Text))

Max Activating Token Index: 619

Text #10

Max Range: 3.4766. Min Range: -3.4766

Max Act: 2.2897. Min Act: -0.0000

Data Index: 1105877 (C4 (Web Text))

Max Activating Token Index: 649

Text #11

Max Range: 3.4766. Min Range: -3.4766

Max Act: 2.6847. Min Act: -0.0000

Data Index: 637575 (C4 (Web Text))

Max Activating Token Index: 80

Text #12

Max Range: 3.4766. Min Range: -3.4766

Max Act: 2.6468. Min Act: -0.0000

Data Index: 39483 (C4 (Web Text))

Max Activating Token Index: 585

Text #13

Max Range: 3.4766. Min Range: -3.4766

Max Act: 2.4504. Min Act: -0.0000

Data Index: 987693 (C4 (Web Text))

Max Activating Token Index: 415

Text #14

Max Range: 3.4766. Min Range: -3.4766

Max Act: 2.4305. Min Act: -0.0000

Data Index: 503671 (C4 (Web Text))

Max Activating Token Index: 751

Text #15

Max Range: 3.4766. Min Range: -3.4766

Max Act: 2.4091. Min Act: -0.0000

Data Index: 1318558 (C4 (Web Text))

Max Activating Token Index: 119

Text #16

Max Range: 3.4766. Min Range: -3.4766

Max Act: 2.2857. Min Act: -0.0000

Data Index: 836582 (C4 (Web Text))

Max Activating Token Index: 824

Text #17

Max Range: 3.4766. Min Range: -3.4766

Max Act: 2.3248. Min Act: -0.0000

Data Index: 906117 (C4 (Web Text))

Max Activating Token Index: 199

Text #18

Max Range: 3.4766. Min Range: -3.4766

Max Act: 2.3339. Min Act: -0.0000

Data Index: 1327932 (C4 (Web Text))

Max Activating Token Index: 792

Text #19

Max Range: 3.4766. Min Range: -3.4766

Max Act: 2.4354. Min Act: -0.0000

Data Index: 1124483 (C4 (Web Text))

Max Activating Token Index: 758