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

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

Neuron 2450 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0131. Min Act: -0.0003

Data Index: 1100354 (C4 (Web Text))

Max Activating Token Index: 110

Text #1

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0122. Min Act: -0.0003

Data Index: 306373 (C4 (Web Text))

Max Activating Token Index: 50

Text #2

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0122. Min Act: -0.0003

Data Index: 654371 (C4 (Web Text))

Max Activating Token Index: 622

Text #3

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0119. Min Act: -0.0003

Data Index: 1301171 (C4 (Web Text))

Max Activating Token Index: 423

Text #4

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0103. Min Act: -0.0003

Data Index: 708003 (C4 (Web Text))

Max Activating Token Index: 370

Text #5

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0100. Min Act: -0.0003

Data Index: 722736 (C4 (Web Text))

Max Activating Token Index: 740

Text #6

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0101. Min Act: -0.0003

Data Index: 382590 (C4 (Web Text))

Max Activating Token Index: 921

Text #7

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0102. Min Act: -0.0003

Data Index: 86676 (C4 (Web Text))

Max Activating Token Index: 833

Text #8

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0093. Min Act: -0.0003

Data Index: 385388 (C4 (Web Text))

Max Activating Token Index: 850

Text #9

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0087. Min Act: -0.0003

Data Index: 886921 (C4 (Web Text))

Max Activating Token Index: 251

Text #10

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0091. Min Act: -0.0003

Data Index: 950777 (C4 (Web Text))

Max Activating Token Index: 448

Text #11

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0094. Min Act: -0.0003

Data Index: 1648771 (Python Code)

Max Activating Token Index: 396

Text #12

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0090. Min Act: -0.0003

Data Index: 956919 (C4 (Web Text))

Max Activating Token Index: 483

Text #13

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0088. Min Act: -0.0003

Data Index: 807788 (C4 (Web Text))

Max Activating Token Index: 323

Text #14

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0094. Min Act: -0.0003

Data Index: 140537 (C4 (Web Text))

Max Activating Token Index: 725

Text #15

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0087. Min Act: -0.0003

Data Index: 687925 (C4 (Web Text))

Max Activating Token Index: 690

Text #16

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0087. Min Act: -0.0003

Data Index: 1489560 (Python Code)

Max Activating Token Index: 354

Text #17

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0085. Min Act: -0.0003

Data Index: 1543721 (Python Code)

Max Activating Token Index: 94

Text #18

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0086. Min Act: -0.0003

Data Index: 882286 (C4 (Web Text))

Max Activating Token Index: 737

Text #19

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0086. Min Act: -0.0003

Data Index: 457826 (C4 (Web Text))

Max Activating Token Index: 698