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

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

Neuron 1300 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: 0.0088. Min Range: -0.0088

Max Act: 0.0088. Min Act: -0.0006

Data Index: 748097 (C4 (Web Text))

Max Activating Token Index: 295

Text #1

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0083. Min Act: -0.0006

Data Index: 684261 (C4 (Web Text))

Max Activating Token Index: 997

Text #2

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0079. Min Act: -0.0006

Data Index: 470755 (C4 (Web Text))

Max Activating Token Index: 91

Text #3

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0079. Min Act: -0.0006

Data Index: 771519 (C4 (Web Text))

Max Activating Token Index: 651

Text #4

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0078. Min Act: -0.0006

Data Index: 448336 (C4 (Web Text))

Max Activating Token Index: 903

Text #5

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0076. Min Act: -0.0006

Data Index: 1183109 (C4 (Web Text))

Max Activating Token Index: 14

Text #6

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0073. Min Act: -0.0006

Data Index: 1337370 (C4 (Web Text))

Max Activating Token Index: 299

Text #7

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0073. Min Act: -0.0006

Data Index: 489724 (C4 (Web Text))

Max Activating Token Index: 897

Text #8

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0072. Min Act: -0.0006

Data Index: 783703 (C4 (Web Text))

Max Activating Token Index: 407

Text #9

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0070. Min Act: -0.0006

Data Index: 391403 (C4 (Web Text))

Max Activating Token Index: 701

Text #10

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0070. Min Act: -0.0006

Data Index: 635095 (C4 (Web Text))

Max Activating Token Index: 26

Text #11

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0070. Min Act: -0.0006

Data Index: 367589 (C4 (Web Text))

Max Activating Token Index: 411

Text #12

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0070. Min Act: -0.0006

Data Index: 739612 (C4 (Web Text))

Max Activating Token Index: 590

Text #13

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0070. Min Act: -0.0005

Data Index: 464106 (C4 (Web Text))

Max Activating Token Index: 996

Text #14

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0069. Min Act: -0.0006

Data Index: 279285 (C4 (Web Text))

Max Activating Token Index: 341

Text #15

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0068. Min Act: -0.0006

Data Index: 1600895 (Python Code)

Max Activating Token Index: 5

Text #16

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0066. Min Act: -0.0006

Data Index: 459011 (C4 (Web Text))

Max Activating Token Index: 193

Text #17

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0069. Min Act: -0.0006

Data Index: 818055 (C4 (Web Text))

Max Activating Token Index: 960

Text #18

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0067. Min Act: -0.0006

Data Index: 1264142 (C4 (Web Text))

Max Activating Token Index: 649

Text #19

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0067. Min Act: -0.0006

Data Index: 821484 (C4 (Web Text))

Max Activating Token Index: 685