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

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

Neuron 1257 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: 0.0105. Min Range: -0.0105

Max Act: 0.0105. Min Act: -0.0006

Data Index: 60483 (C4 (Web Text))

Max Activating Token Index: 115

Text #1

Max Range: 0.0105. Min Range: -0.0105

Max Act: 0.0098. Min Act: -0.0006

Data Index: 716984 (C4 (Web Text))

Max Activating Token Index: 520

Text #2

Max Range: 0.0105. Min Range: -0.0105

Max Act: 0.0096. Min Act: -0.0006

Data Index: 476827 (C4 (Web Text))

Max Activating Token Index: 854

Text #3

Max Range: 0.0105. Min Range: -0.0105

Max Act: 0.0095. Min Act: -0.0006

Data Index: 436452 (C4 (Web Text))

Max Activating Token Index: 418

Text #4

Max Range: 0.0105. Min Range: -0.0105

Max Act: 0.0095. Min Act: -0.0006

Data Index: 660944 (C4 (Web Text))

Max Activating Token Index: 515

Text #5

Max Range: 0.0105. Min Range: -0.0105

Max Act: 0.0094. Min Act: -0.0006

Data Index: 738128 (C4 (Web Text))

Max Activating Token Index: 881

Text #6

Max Range: 0.0105. Min Range: -0.0105

Max Act: 0.0093. Min Act: -0.0006

Data Index: 545896 (C4 (Web Text))

Max Activating Token Index: 332

Text #7

Max Range: 0.0105. Min Range: -0.0105

Max Act: 0.0090. Min Act: -0.0006

Data Index: 488941 (C4 (Web Text))

Max Activating Token Index: 828

Text #8

Max Range: 0.0105. Min Range: -0.0105

Max Act: 0.0089. Min Act: -0.0007

Data Index: 452737 (C4 (Web Text))

Max Activating Token Index: 284

Text #9

Max Range: 0.0105. Min Range: -0.0105

Max Act: 0.0089. Min Act: -0.0006

Data Index: 872735 (C4 (Web Text))

Max Activating Token Index: 364

Text #10

Max Range: 0.0105. Min Range: -0.0105

Max Act: 0.0090. Min Act: -0.0006

Data Index: 175833 (C4 (Web Text))

Max Activating Token Index: 890

Text #11

Max Range: 0.0105. Min Range: -0.0105

Max Act: 0.0089. Min Act: -0.0006

Data Index: 1284923 (C4 (Web Text))

Max Activating Token Index: 517

Text #12

Max Range: 0.0105. Min Range: -0.0105

Max Act: 0.0088. Min Act: -0.0006

Data Index: 657948 (C4 (Web Text))

Max Activating Token Index: 551

Text #13

Max Range: 0.0105. Min Range: -0.0105

Max Act: 0.0088. Min Act: -0.0006

Data Index: 843741 (C4 (Web Text))

Max Activating Token Index: 713

Text #14

Max Range: 0.0105. Min Range: -0.0105

Max Act: 0.0090. Min Act: -0.0006

Data Index: 291103 (C4 (Web Text))

Max Activating Token Index: 563

Text #15

Max Range: 0.0105. Min Range: -0.0105

Max Act: 0.0087. Min Act: -0.0006

Data Index: 1329551 (C4 (Web Text))

Max Activating Token Index: 39

Text #16

Max Range: 0.0105. Min Range: -0.0105

Max Act: 0.0089. Min Act: -0.0006

Data Index: 507492 (C4 (Web Text))

Max Activating Token Index: 103

Text #17

Max Range: 0.0105. Min Range: -0.0105

Max Act: 0.0087. Min Act: -0.0006

Data Index: 21995 (C4 (Web Text))

Max Activating Token Index: 372

Text #18

Max Range: 0.0105. Min Range: -0.0105

Max Act: 0.0086. Min Act: -0.0006

Data Index: 459156 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.0105. Min Range: -0.0105

Max Act: 0.0088. Min Act: -0.0006

Data Index: 927243 (C4 (Web Text))

Max Activating Token Index: 757