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

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

Neuron 1545 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0103. Min Range: -0.0103

Max Act: 0.0103. Min Act: -0.0006

Data Index: 155263 (C4 (Web Text))

Max Activating Token Index: 897

Text #1

Max Range: 0.0103. Min Range: -0.0103

Max Act: 0.0098. Min Act: -0.0006

Data Index: 1112866 (C4 (Web Text))

Max Activating Token Index: 567

Text #2

Max Range: 0.0103. Min Range: -0.0103

Max Act: 0.0094. Min Act: -0.0006

Data Index: 406752 (C4 (Web Text))

Max Activating Token Index: 54

Text #3

Max Range: 0.0103. Min Range: -0.0103

Max Act: 0.0093. Min Act: -0.0006

Data Index: 275303 (C4 (Web Text))

Max Activating Token Index: 911

Text #4

Max Range: 0.0103. Min Range: -0.0103

Max Act: 0.0092. Min Act: -0.0005

Data Index: 1010532 (C4 (Web Text))

Max Activating Token Index: 915

Text #5

Max Range: 0.0103. Min Range: -0.0103

Max Act: 0.0092. Min Act: -0.0006

Data Index: 1168180 (C4 (Web Text))

Max Activating Token Index: 543

Text #6

Max Range: 0.0103. Min Range: -0.0103

Max Act: 0.0091. Min Act: -0.0005

Data Index: 540656 (C4 (Web Text))

Max Activating Token Index: 983

Text #7

Max Range: 0.0103. Min Range: -0.0103

Max Act: 0.0091. Min Act: -0.0006

Data Index: 537980 (C4 (Web Text))

Max Activating Token Index: 293

Text #8

Max Range: 0.0103. Min Range: -0.0103

Max Act: 0.0091. Min Act: -0.0005

Data Index: 951691 (C4 (Web Text))

Max Activating Token Index: 769

Text #9

Max Range: 0.0103. Min Range: -0.0103

Max Act: 0.0090. Min Act: -0.0006

Data Index: 677686 (C4 (Web Text))

Max Activating Token Index: 323

Text #10

Max Range: 0.0103. Min Range: -0.0103

Max Act: 0.0092. Min Act: -0.0006

Data Index: 879803 (C4 (Web Text))

Max Activating Token Index: 243

Text #11

Max Range: 0.0103. Min Range: -0.0103

Max Act: 0.0090. Min Act: -0.0005

Data Index: 1532667 (Python Code)

Max Activating Token Index: 627

Text #12

Max Range: 0.0103. Min Range: -0.0103

Max Act: 0.0089. Min Act: -0.0006

Data Index: 1379248 (Python Code)

Max Activating Token Index: 330

Text #13

Max Range: 0.0103. Min Range: -0.0103

Max Act: 0.0089. Min Act: -0.0006

Data Index: 1119557 (C4 (Web Text))

Max Activating Token Index: 583

Text #14

Max Range: 0.0103. Min Range: -0.0103

Max Act: 0.0089. Min Act: -0.0005

Data Index: 47178 (C4 (Web Text))

Max Activating Token Index: 735

Text #15

Max Range: 0.0103. Min Range: -0.0103

Max Act: 0.0091. Min Act: -0.0005

Data Index: 607809 (C4 (Web Text))

Max Activating Token Index: 797

Text #16

Max Range: 0.0103. Min Range: -0.0103

Max Act: 0.0086. Min Act: -0.0006

Data Index: 872840 (C4 (Web Text))

Max Activating Token Index: 942

Text #17

Max Range: 0.0103. Min Range: -0.0103

Max Act: 0.0090. Min Act: -0.0006

Data Index: 1283631 (C4 (Web Text))

Max Activating Token Index: 804

Text #18

Max Range: 0.0103. Min Range: -0.0103

Max Act: 0.0089. Min Act: -0.0005

Data Index: 529118 (C4 (Web Text))

Max Activating Token Index: 865

Text #19

Max Range: 0.0103. Min Range: -0.0103

Max Act: 0.0088. Min Act: -0.0006

Data Index: 849465 (C4 (Web Text))

Max Activating Token Index: 614