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

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

Neuron 1257 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1197. Min Range: -0.1197

Max Act: 0.1197. Min Act: -0.0000

Data Index: 1273059 (C4 (Web Text))

Max Activating Token Index: 493

Text #1

Max Range: 0.1197. Min Range: -0.1197

Max Act: 0.1066. Min Act: -0.0000

Data Index: 651123 (C4 (Web Text))

Max Activating Token Index: 982

Text #2

Max Range: 0.1197. Min Range: -0.1197

Max Act: 0.0947. Min Act: -0.0000

Data Index: 689195 (C4 (Web Text))

Max Activating Token Index: 1020

Text #3

Max Range: 0.1197. Min Range: -0.1197

Max Act: 0.1000. Min Act: -0.0000

Data Index: 672979 (C4 (Web Text))

Max Activating Token Index: 141

Text #4

Max Range: 0.1197. Min Range: -0.1197

Max Act: 0.0906. Min Act: -0.0000

Data Index: 751891 (C4 (Web Text))

Max Activating Token Index: 735

Text #5

Max Range: 0.1197. Min Range: -0.1197

Max Act: 0.1011. Min Act: -0.0000

Data Index: 397436 (C4 (Web Text))

Max Activating Token Index: 61

Text #6

Max Range: 0.1197. Min Range: -0.1197

Max Act: 0.0944. Min Act: -0.0000

Data Index: 233253 (C4 (Web Text))

Max Activating Token Index: 265

Text #7

Max Range: 0.1197. Min Range: -0.1197

Max Act: 0.0995. Min Act: -0.0000

Data Index: 1171023 (C4 (Web Text))

Max Activating Token Index: 423

Text #8

Max Range: 0.1197. Min Range: -0.1197

Max Act: 0.0909. Min Act: -0.0000

Data Index: 303849 (C4 (Web Text))

Max Activating Token Index: 323

Text #9

Max Range: 0.1197. Min Range: -0.1197

Max Act: 0.0890. Min Act: -0.0000

Data Index: 548665 (C4 (Web Text))

Max Activating Token Index: 1004

Text #10

Max Range: 0.1197. Min Range: -0.1197

Max Act: 0.0899. Min Act: -0.0000

Data Index: 1351661 (C4 (Web Text))

Max Activating Token Index: 428

Text #11

Max Range: 0.1197. Min Range: -0.1197

Max Act: 0.0878. Min Act: -0.0000

Data Index: 809274 (C4 (Web Text))

Max Activating Token Index: 182

Text #12

Max Range: 0.1197. Min Range: -0.1197

Max Act: 0.0882. Min Act: -0.0000

Data Index: 988567 (C4 (Web Text))

Max Activating Token Index: 128

Text #13

Max Range: 0.1197. Min Range: -0.1197

Max Act: 0.0921. Min Act: -0.0000

Data Index: 879537 (C4 (Web Text))

Max Activating Token Index: 889

Text #14

Max Range: 0.1197. Min Range: -0.1197

Max Act: 0.0915. Min Act: -0.0000

Data Index: 224749 (C4 (Web Text))

Max Activating Token Index: 1006

Text #15

Max Range: 0.1197. Min Range: -0.1197

Max Act: 0.0920. Min Act: -0.0000

Data Index: 966518 (C4 (Web Text))

Max Activating Token Index: 922

Text #16

Max Range: 0.1197. Min Range: -0.1197

Max Act: 0.0815. Min Act: -0.0000

Data Index: 654760 (C4 (Web Text))

Max Activating Token Index: 632

Text #17

Max Range: 0.1197. Min Range: -0.1197

Max Act: 0.0920. Min Act: -0.0000

Data Index: 5751 (C4 (Web Text))

Max Activating Token Index: 216

Text #18

Max Range: 0.1197. Min Range: -0.1197

Max Act: 0.0825. Min Act: -0.0000

Data Index: 81778 (C4 (Web Text))

Max Activating Token Index: 299

Text #19

Max Range: 0.1197. Min Range: -0.1197

Max Act: 0.0914. Min Act: -0.0000

Data Index: 392475 (C4 (Web Text))

Max Activating Token Index: 956