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

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

Neuron 197 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0100. Min Act: -0.0006

Data Index: 500683 (C4 (Web Text))

Max Activating Token Index: 1000

Text #1

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0099. Min Act: -0.0006

Data Index: 1301597 (C4 (Web Text))

Max Activating Token Index: 1005

Text #2

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0101. Min Act: -0.0006

Data Index: 1078914 (C4 (Web Text))

Max Activating Token Index: 867

Text #3

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0089. Min Act: -0.0006

Data Index: 237632 (C4 (Web Text))

Max Activating Token Index: 1011

Text #4

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0089. Min Act: -0.0006

Data Index: 1059312 (C4 (Web Text))

Max Activating Token Index: 962

Text #5

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0091. Min Act: -0.0006

Data Index: 298832 (C4 (Web Text))

Max Activating Token Index: 997

Text #6

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0090. Min Act: -0.0006

Data Index: 297667 (C4 (Web Text))

Max Activating Token Index: 444

Text #7

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0090. Min Act: -0.0006

Data Index: 155230 (C4 (Web Text))

Max Activating Token Index: 850

Text #8

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0090. Min Act: -0.0006

Data Index: 714277 (C4 (Web Text))

Max Activating Token Index: 998

Text #9

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0090. Min Act: -0.0006

Data Index: 104498 (C4 (Web Text))

Max Activating Token Index: 349

Text #10

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0090. Min Act: -0.0006

Data Index: 42808 (C4 (Web Text))

Max Activating Token Index: 296

Text #11

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0087. Min Act: -0.0006

Data Index: 1089107 (C4 (Web Text))

Max Activating Token Index: 1009

Text #12

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0089. Min Act: -0.0006

Data Index: 1323391 (C4 (Web Text))

Max Activating Token Index: 464

Text #13

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0089. Min Act: -0.0006

Data Index: 538637 (C4 (Web Text))

Max Activating Token Index: 640

Text #14

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0091. Min Act: -0.0006

Data Index: 837153 (C4 (Web Text))

Max Activating Token Index: 535

Text #15

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0086. Min Act: -0.0006

Data Index: 136014 (C4 (Web Text))

Max Activating Token Index: 989

Text #16

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0088. Min Act: -0.0006

Data Index: 454213 (C4 (Web Text))

Max Activating Token Index: 930

Text #17

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0086. Min Act: -0.0006

Data Index: 1054465 (C4 (Web Text))

Max Activating Token Index: 913

Text #18

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0085. Min Act: -0.0006

Data Index: 1207474 (C4 (Web Text))

Max Activating Token Index: 916

Text #19

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0085. Min Act: -0.0006

Data Index: 198277 (C4 (Web Text))

Max Activating Token Index: 859