Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1197 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0103. Min Range: -0.0103

Max Act: 0.0103. Min Act: -0.0005

Data Index: 304336 (C4 (Web Text))

Max Activating Token Index: 329

Text #1

Max Range: 0.0103. Min Range: -0.0103

Max Act: 0.0098. Min Act: -0.0004

Data Index: 483195 (C4 (Web Text))

Max Activating Token Index: 582

Text #2

Max Range: 0.0103. Min Range: -0.0103

Max Act: 0.0099. Min Act: -0.0005

Data Index: 74666 (C4 (Web Text))

Max Activating Token Index: 180

Text #3

Max Range: 0.0103. Min Range: -0.0103

Max Act: 0.0100. Min Act: -0.0005

Data Index: 645616 (C4 (Web Text))

Max Activating Token Index: 126

Text #4

Max Range: 0.0103. Min Range: -0.0103

Max Act: 0.0099. Min Act: -0.0004

Data Index: 1147700 (C4 (Web Text))

Max Activating Token Index: 562

Text #5

Max Range: 0.0103. Min Range: -0.0103

Max Act: 0.0097. Min Act: -0.0004

Data Index: 689672 (C4 (Web Text))

Max Activating Token Index: 442

Text #6

Max Range: 0.0103. Min Range: -0.0103

Max Act: 0.0095. Min Act: -0.0005

Data Index: 1091748 (C4 (Web Text))

Max Activating Token Index: 591

Text #7

Max Range: 0.0103. Min Range: -0.0103

Max Act: 0.0096. Min Act: -0.0004

Data Index: 511942 (C4 (Web Text))

Max Activating Token Index: 45

Text #8

Max Range: 0.0103. Min Range: -0.0103

Max Act: 0.0092. Min Act: -0.0004

Data Index: 1634195 (Python Code)

Max Activating Token Index: 326

Text #9

Max Range: 0.0103. Min Range: -0.0103

Max Act: 0.0093. Min Act: -0.0005

Data Index: 310081 (C4 (Web Text))

Max Activating Token Index: 168

Text #10

Max Range: 0.0103. Min Range: -0.0103

Max Act: 0.0096. Min Act: -0.0005

Data Index: 353621 (C4 (Web Text))

Max Activating Token Index: 140

Text #11

Max Range: 0.0103. Min Range: -0.0103

Max Act: 0.0093. Min Act: -0.0004

Data Index: 881070 (C4 (Web Text))

Max Activating Token Index: 117

Text #12

Max Range: 0.0103. Min Range: -0.0103

Max Act: 0.0092. Min Act: -0.0004

Data Index: 223709 (C4 (Web Text))

Max Activating Token Index: 671

Text #13

Max Range: 0.0103. Min Range: -0.0103

Max Act: 0.0092. Min Act: -0.0005

Data Index: 602775 (C4 (Web Text))

Max Activating Token Index: 422

Text #14

Max Range: 0.0103. Min Range: -0.0103

Max Act: 0.0093. Min Act: -0.0005

Data Index: 250292 (C4 (Web Text))

Max Activating Token Index: 180

Text #15

Max Range: 0.0103. Min Range: -0.0103

Max Act: 0.0091. Min Act: -0.0005

Data Index: 7238 (C4 (Web Text))

Max Activating Token Index: 636

Text #16

Max Range: 0.0103. Min Range: -0.0103

Max Act: 0.0092. Min Act: -0.0005

Data Index: 424163 (C4 (Web Text))

Max Activating Token Index: 374

Text #17

Max Range: 0.0103. Min Range: -0.0103

Max Act: 0.0092. Min Act: -0.0004

Data Index: 795302 (C4 (Web Text))

Max Activating Token Index: 962

Text #18

Max Range: 0.0103. Min Range: -0.0103

Max Act: 0.0092. Min Act: -0.0005

Data Index: 599042 (C4 (Web Text))

Max Activating Token Index: 555

Text #19

Max Range: 0.0103. Min Range: -0.0103

Max Act: 0.0093. Min Act: -0.0005

Data Index: 1929 (C4 (Web Text))

Max Activating Token Index: 48