Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2739 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 6.0073. Min Range: -6.0073

Max Act: 5.8400. Min Act: -0.0000

Data Index: 650927 (C4 (Web Text))

Max Activating Token Index: 958

Text #1

Max Range: 6.0073. Min Range: -6.0073

Max Act: 6.0073. Min Act: -0.0000

Data Index: 189987 (C4 (Web Text))

Max Activating Token Index: 820

Text #2

Max Range: 6.0073. Min Range: -6.0073

Max Act: 5.9858. Min Act: -0.0000

Data Index: 793023 (C4 (Web Text))

Max Activating Token Index: 404

Text #3

Max Range: 6.0073. Min Range: -6.0073

Max Act: 5.8381. Min Act: -0.0000

Data Index: 653055 (C4 (Web Text))

Max Activating Token Index: 482

Text #4

Max Range: 6.0073. Min Range: -6.0073

Max Act: 5.8613. Min Act: -0.0000

Data Index: 651006 (C4 (Web Text))

Max Activating Token Index: 339

Text #5

Max Range: 6.0073. Min Range: -6.0073

Max Act: 5.8000. Min Act: -0.0000

Data Index: 88671 (C4 (Web Text))

Max Activating Token Index: 1009

Text #6

Max Range: 6.0073. Min Range: -6.0073

Max Act: 5.8099. Min Act: -0.0000

Data Index: 113487 (C4 (Web Text))

Max Activating Token Index: 392

Text #7

Max Range: 6.0073. Min Range: -6.0073

Max Act: 5.5792. Min Act: -0.0000

Data Index: 201862 (C4 (Web Text))

Max Activating Token Index: 884

Text #8

Max Range: 6.0073. Min Range: -6.0073

Max Act: 5.5715. Min Act: -0.0000

Data Index: 734632 (C4 (Web Text))

Max Activating Token Index: 1001

Text #9

Max Range: 6.0073. Min Range: -6.0073

Max Act: 5.2930. Min Act: -0.0000

Data Index: 1252400 (C4 (Web Text))

Max Activating Token Index: 127

Text #10

Max Range: 6.0073. Min Range: -6.0073

Max Act: 5.6216. Min Act: -0.0000

Data Index: 964883 (C4 (Web Text))

Max Activating Token Index: 937

Text #11

Max Range: 6.0073. Min Range: -6.0073

Max Act: 5.0512. Min Act: -0.0000

Data Index: 429382 (C4 (Web Text))

Max Activating Token Index: 748

Text #12

Max Range: 6.0073. Min Range: -6.0073

Max Act: 5.3909. Min Act: -0.0000

Data Index: 1302364 (C4 (Web Text))

Max Activating Token Index: 906

Text #13

Max Range: 6.0073. Min Range: -6.0073

Max Act: 5.3706. Min Act: -0.0000

Data Index: 177157 (C4 (Web Text))

Max Activating Token Index: 603

Text #14

Max Range: 6.0073. Min Range: -6.0073

Max Act: 5.2400. Min Act: -0.0000

Data Index: 149199 (C4 (Web Text))

Max Activating Token Index: 495

Text #15

Max Range: 6.0073. Min Range: -6.0073

Max Act: 5.3195. Min Act: -0.0000

Data Index: 1135591 (C4 (Web Text))

Max Activating Token Index: 434

Text #16

Max Range: 6.0073. Min Range: -6.0073

Max Act: 5.0987. Min Act: -0.0000

Data Index: 1253137 (C4 (Web Text))

Max Activating Token Index: 786

Text #17

Max Range: 6.0073. Min Range: -6.0073

Max Act: 4.8481. Min Act: -0.0000

Data Index: 1059261 (C4 (Web Text))

Max Activating Token Index: 429

Text #18

Max Range: 6.0073. Min Range: -6.0073

Max Act: 4.8448. Min Act: -0.0000

Data Index: 312294 (C4 (Web Text))

Max Activating Token Index: 557

Text #19

Max Range: 6.0073. Min Range: -6.0073

Max Act: 5.2008. Min Act: -0.0000

Data Index: 481518 (C4 (Web Text))

Max Activating Token Index: 721