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

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

Neuron 773 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: 0.0099. Min Range: -0.0099

Max Act: 0.0099. Min Act: -0.0006

Data Index: 193419 (C4 (Web Text))

Max Activating Token Index: 866

Text #1

Max Range: 0.0099. Min Range: -0.0099

Max Act: 0.0097. Min Act: -0.0006

Data Index: 1101287 (C4 (Web Text))

Max Activating Token Index: 549

Text #2

Max Range: 0.0099. Min Range: -0.0099

Max Act: 0.0096. Min Act: -0.0006

Data Index: 1437662 (Python Code)

Max Activating Token Index: 971

Text #3

Max Range: 0.0099. Min Range: -0.0099

Max Act: 0.0096. Min Act: -0.0006

Data Index: 317422 (C4 (Web Text))

Max Activating Token Index: 156

Text #4

Max Range: 0.0099. Min Range: -0.0099

Max Act: 0.0089. Min Act: -0.0006

Data Index: 1184808 (C4 (Web Text))

Max Activating Token Index: 124

Text #5

Max Range: 0.0099. Min Range: -0.0099

Max Act: 0.0091. Min Act: -0.0006

Data Index: 197203 (C4 (Web Text))

Max Activating Token Index: 256

Text #6

Max Range: 0.0099. Min Range: -0.0099

Max Act: 0.0090. Min Act: -0.0006

Data Index: 494763 (C4 (Web Text))

Max Activating Token Index: 1017

Text #7

Max Range: 0.0099. Min Range: -0.0099

Max Act: 0.0088. Min Act: -0.0006

Data Index: 1216605 (C4 (Web Text))

Max Activating Token Index: 983

Text #8

Max Range: 0.0099. Min Range: -0.0099

Max Act: 0.0089. Min Act: -0.0006

Data Index: 1148831 (C4 (Web Text))

Max Activating Token Index: 903

Text #9

Max Range: 0.0099. Min Range: -0.0099

Max Act: 0.0090. Min Act: -0.0006

Data Index: 794644 (C4 (Web Text))

Max Activating Token Index: 311

Text #10

Max Range: 0.0099. Min Range: -0.0099

Max Act: 0.0087. Min Act: -0.0006

Data Index: 905574 (C4 (Web Text))

Max Activating Token Index: 1021

Text #11

Max Range: 0.0099. Min Range: -0.0099

Max Act: 0.0088. Min Act: -0.0006

Data Index: 1180575 (C4 (Web Text))

Max Activating Token Index: 87

Text #12

Max Range: 0.0099. Min Range: -0.0099

Max Act: 0.0087. Min Act: -0.0005

Data Index: 1555835 (Python Code)

Max Activating Token Index: 60

Text #13

Max Range: 0.0099. Min Range: -0.0099

Max Act: 0.0088. Min Act: -0.0005

Data Index: 1628163 (Python Code)

Max Activating Token Index: 459

Text #14

Max Range: 0.0099. Min Range: -0.0099

Max Act: 0.0086. Min Act: -0.0006

Data Index: 448687 (C4 (Web Text))

Max Activating Token Index: 659

Text #15

Max Range: 0.0099. Min Range: -0.0099

Max Act: 0.0086. Min Act: -0.0006

Data Index: 115879 (C4 (Web Text))

Max Activating Token Index: 21

Text #16

Max Range: 0.0099. Min Range: -0.0099

Max Act: 0.0084. Min Act: -0.0006

Data Index: 334868 (C4 (Web Text))

Max Activating Token Index: 376

Text #17

Max Range: 0.0099. Min Range: -0.0099

Max Act: 0.0086. Min Act: -0.0006

Data Index: 331627 (C4 (Web Text))

Max Activating Token Index: 188

Text #18

Max Range: 0.0099. Min Range: -0.0099

Max Act: 0.0086. Min Act: -0.0006

Data Index: 1379217 (Python Code)

Max Activating Token Index: 627

Text #19

Max Range: 0.0099. Min Range: -0.0099

Max Act: 0.0085. Min Act: -0.0006

Data Index: 278680 (C4 (Web Text))

Max Activating Token Index: 1007