Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 274 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0076. Min Range: -0.0076

Max Act: 0.0076. Min Act: -0.0005

Data Index: 709513 (C4 (Web Text))

Max Activating Token Index: 622

Text #1

Max Range: 0.0076. Min Range: -0.0076

Max Act: 0.0074. Min Act: -0.0004

Data Index: 48030 (C4 (Web Text))

Max Activating Token Index: 548

Text #2

Max Range: 0.0076. Min Range: -0.0076

Max Act: 0.0074. Min Act: -0.0004

Data Index: 1329747 (C4 (Web Text))

Max Activating Token Index: 511

Text #3

Max Range: 0.0076. Min Range: -0.0076

Max Act: 0.0076. Min Act: -0.0005

Data Index: 818757 (C4 (Web Text))

Max Activating Token Index: 889

Text #4

Max Range: 0.0076. Min Range: -0.0076

Max Act: 0.0073. Min Act: -0.0004

Data Index: 275331 (C4 (Web Text))

Max Activating Token Index: 936

Text #5

Max Range: 0.0076. Min Range: -0.0076

Max Act: 0.0071. Min Act: -0.0006

Data Index: 457831 (C4 (Web Text))

Max Activating Token Index: 540

Text #6

Max Range: 0.0076. Min Range: -0.0076

Max Act: 0.0070. Min Act: -0.0004

Data Index: 460100 (C4 (Web Text))

Max Activating Token Index: 637

Text #7

Max Range: 0.0076. Min Range: -0.0076

Max Act: 0.0074. Min Act: -0.0004

Data Index: 1319818 (C4 (Web Text))

Max Activating Token Index: 342

Text #8

Max Range: 0.0076. Min Range: -0.0076

Max Act: 0.0075. Min Act: -0.0005

Data Index: 1622482 (Python Code)

Max Activating Token Index: 728

Text #9

Max Range: 0.0076. Min Range: -0.0076

Max Act: 0.0068. Min Act: -0.0004

Data Index: 165651 (C4 (Web Text))

Max Activating Token Index: 661

Text #10

Max Range: 0.0076. Min Range: -0.0076

Max Act: 0.0070. Min Act: -0.0003

Data Index: 408498 (C4 (Web Text))

Max Activating Token Index: 509

Text #11

Max Range: 0.0076. Min Range: -0.0076

Max Act: 0.0069. Min Act: -0.0005

Data Index: 1343709 (C4 (Web Text))

Max Activating Token Index: 404

Text #12

Max Range: 0.0076. Min Range: -0.0076

Max Act: 0.0068. Min Act: -0.0004

Data Index: 318600 (C4 (Web Text))

Max Activating Token Index: 550

Text #13

Max Range: 0.0076. Min Range: -0.0076

Max Act: 0.0067. Min Act: -0.0003

Data Index: 1301785 (C4 (Web Text))

Max Activating Token Index: 594

Text #14

Max Range: 0.0076. Min Range: -0.0076

Max Act: 0.0068. Min Act: -0.0005

Data Index: 912518 (C4 (Web Text))

Max Activating Token Index: 747

Text #15

Max Range: 0.0076. Min Range: -0.0076

Max Act: 0.0067. Min Act: -0.0003

Data Index: 355799 (C4 (Web Text))

Max Activating Token Index: 989

Text #16

Max Range: 0.0076. Min Range: -0.0076

Max Act: 0.0068. Min Act: -0.0004

Data Index: 519399 (C4 (Web Text))

Max Activating Token Index: 723

Text #17

Max Range: 0.0076. Min Range: -0.0076

Max Act: 0.0067. Min Act: -0.0005

Data Index: 1523119 (Python Code)

Max Activating Token Index: 407

Text #18

Max Range: 0.0076. Min Range: -0.0076

Max Act: 0.0068. Min Act: -0.0004

Data Index: 242713 (C4 (Web Text))

Max Activating Token Index: 647

Text #19

Max Range: 0.0076. Min Range: -0.0076

Max Act: 0.0067. Min Act: -0.0004

Data Index: 686717 (C4 (Web Text))

Max Activating Token Index: 527