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

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

Neuron 1127 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0948. Min Act: -0.0003

Data Index: 1118947 (C4 (Web Text))

Max Activating Token Index: 118

Text #1

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0964. Min Act: -0.0003

Data Index: 874820 (C4 (Web Text))

Max Activating Token Index: 246

Text #2

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0913. Min Act: -0.0002

Data Index: 557266 (C4 (Web Text))

Max Activating Token Index: 306

Text #3

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0916. Min Act: -0.0003

Data Index: 189811 (C4 (Web Text))

Max Activating Token Index: 1011

Text #4

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0934. Min Act: -0.0003

Data Index: 1164080 (C4 (Web Text))

Max Activating Token Index: 592

Text #5

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0927. Min Act: -0.0003

Data Index: 1195157 (C4 (Web Text))

Max Activating Token Index: 383

Text #6

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0854. Min Act: -0.0003

Data Index: 1172021 (C4 (Web Text))

Max Activating Token Index: 426

Text #7

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0849. Min Act: -0.0003

Data Index: 407942 (C4 (Web Text))

Max Activating Token Index: 71

Text #8

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0871. Min Act: -0.0003

Data Index: 1259064 (C4 (Web Text))

Max Activating Token Index: 232

Text #9

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0816. Min Act: -0.0002

Data Index: 125096 (C4 (Web Text))

Max Activating Token Index: 160

Text #10

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0842. Min Act: -0.0004

Data Index: 511028 (C4 (Web Text))

Max Activating Token Index: 221

Text #11

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0862. Min Act: -0.0003

Data Index: 746082 (C4 (Web Text))

Max Activating Token Index: 408

Text #12

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0863. Min Act: -0.0002

Data Index: 444446 (C4 (Web Text))

Max Activating Token Index: 601

Text #13

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0838. Min Act: -0.0003

Data Index: 1156284 (C4 (Web Text))

Max Activating Token Index: 31

Text #14

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0862. Min Act: -0.0003

Data Index: 1064895 (C4 (Web Text))

Max Activating Token Index: 699

Text #15

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0865. Min Act: -0.0003

Data Index: 1010609 (C4 (Web Text))

Max Activating Token Index: 213

Text #16

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0849. Min Act: -0.0003

Data Index: 392010 (C4 (Web Text))

Max Activating Token Index: 893

Text #17

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0849. Min Act: -0.0003

Data Index: 309073 (C4 (Web Text))

Max Activating Token Index: 126

Text #18

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0830. Min Act: -0.0003

Data Index: 660111 (C4 (Web Text))

Max Activating Token Index: 362

Text #19

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0840. Min Act: -0.0003

Data Index: 351776 (C4 (Web Text))

Max Activating Token Index: 645