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

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

Neuron 1500 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0106. Min Act: -0.0006

Data Index: 30894 (C4 (Web Text))

Max Activating Token Index: 841

Text #1

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0107. Min Act: -0.0006

Data Index: 1270526 (C4 (Web Text))

Max Activating Token Index: 40

Text #2

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0103. Min Act: -0.0006

Data Index: 647018 (C4 (Web Text))

Max Activating Token Index: 880

Text #3

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0102. Min Act: -0.0006

Data Index: 46356 (C4 (Web Text))

Max Activating Token Index: 32

Text #4

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0096. Min Act: -0.0006

Data Index: 1113094 (C4 (Web Text))

Max Activating Token Index: 793

Text #5

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0097. Min Act: -0.0006

Data Index: 249529 (C4 (Web Text))

Max Activating Token Index: 453

Text #6

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0099. Min Act: -0.0006

Data Index: 13756 (C4 (Web Text))

Max Activating Token Index: 404

Text #7

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0091. Min Act: -0.0006

Data Index: 1193520 (C4 (Web Text))

Max Activating Token Index: 946

Text #8

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0098. Min Act: -0.0006

Data Index: 1157248 (C4 (Web Text))

Max Activating Token Index: 428

Text #9

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0098. Min Act: -0.0006

Data Index: 235469 (C4 (Web Text))

Max Activating Token Index: 533

Text #10

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0094. Min Act: -0.0006

Data Index: 530626 (C4 (Web Text))

Max Activating Token Index: 1006

Text #11

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0090. Min Act: -0.0006

Data Index: 949479 (C4 (Web Text))

Max Activating Token Index: 989

Text #12

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0091. Min Act: -0.0006

Data Index: 798015 (C4 (Web Text))

Max Activating Token Index: 6

Text #13

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0094. Min Act: -0.0006

Data Index: 248330 (C4 (Web Text))

Max Activating Token Index: 407

Text #14

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0093. Min Act: -0.0006

Data Index: 1201382 (C4 (Web Text))

Max Activating Token Index: 939

Text #15

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0091. Min Act: -0.0006

Data Index: 888670 (C4 (Web Text))

Max Activating Token Index: 947

Text #16

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0090. Min Act: -0.0006

Data Index: 1329141 (C4 (Web Text))

Max Activating Token Index: 279

Text #17

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0093. Min Act: -0.0006

Data Index: 1106355 (C4 (Web Text))

Max Activating Token Index: 781

Text #18

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0090. Min Act: -0.0005

Data Index: 8041 (C4 (Web Text))

Max Activating Token Index: 185

Text #19

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0092. Min Act: -0.0006

Data Index: 209901 (C4 (Web Text))

Max Activating Token Index: 497