Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1524 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0773. Min Act: -0.0004

Data Index: 43006 (C4 (Web Text))

Max Activating Token Index: 652

Text #1

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0772. Min Act: -0.0004

Data Index: 1282337 (C4 (Web Text))

Max Activating Token Index: 869

Text #2

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0672. Min Act: -0.0004

Data Index: 951830 (C4 (Web Text))

Max Activating Token Index: 25

Text #3

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0637. Min Act: -0.0004

Data Index: 779231 (C4 (Web Text))

Max Activating Token Index: 67

Text #4

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0628. Min Act: -0.0004

Data Index: 523213 (C4 (Web Text))

Max Activating Token Index: 331

Text #5

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0601. Min Act: -0.0004

Data Index: 262155 (C4 (Web Text))

Max Activating Token Index: 680

Text #6

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0597. Min Act: -0.0004

Data Index: 1113090 (C4 (Web Text))

Max Activating Token Index: 116

Text #7

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0569. Min Act: -0.0004

Data Index: 753126 (C4 (Web Text))

Max Activating Token Index: 71

Text #8

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0585. Min Act: -0.0004

Data Index: 134146 (C4 (Web Text))

Max Activating Token Index: 157

Text #9

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0584. Min Act: -0.0004

Data Index: 170367 (C4 (Web Text))

Max Activating Token Index: 111

Text #10

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0578. Min Act: -0.0004

Data Index: 703199 (C4 (Web Text))

Max Activating Token Index: 122

Text #11

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0598. Min Act: -0.0004

Data Index: 489642 (C4 (Web Text))

Max Activating Token Index: 263

Text #12

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0592. Min Act: -0.0004

Data Index: 1279856 (C4 (Web Text))

Max Activating Token Index: 22

Text #13

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0565. Min Act: -0.0004

Data Index: 1124702 (C4 (Web Text))

Max Activating Token Index: 34

Text #14

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0567. Min Act: -0.0004

Data Index: 105222 (C4 (Web Text))

Max Activating Token Index: 455

Text #15

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0583. Min Act: -0.0004

Data Index: 449995 (C4 (Web Text))

Max Activating Token Index: 759

Text #16

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0537. Min Act: -0.0004

Data Index: 287716 (C4 (Web Text))

Max Activating Token Index: 99

Text #17

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0558. Min Act: -0.0004

Data Index: 1081603 (C4 (Web Text))

Max Activating Token Index: 969

Text #18

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0579. Min Act: -0.0004

Data Index: 988995 (C4 (Web Text))

Max Activating Token Index: 669

Text #19

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0530. Min Act: -0.0004

Data Index: 554431 (C4 (Web Text))

Max Activating Token Index: 225