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

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

Neuron 3281 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8051. Min Range: -0.8051

Max Act: 0.8051. Min Act: -0.0000

Data Index: 567946 (C4 (Web Text))

Max Activating Token Index: 735

Text #1

Max Range: 0.8051. Min Range: -0.8051

Max Act: 0.7210. Min Act: -0.0000

Data Index: 1586510 (Python Code)

Max Activating Token Index: 369

Text #2

Max Range: 0.8051. Min Range: -0.8051

Max Act: 0.6381. Min Act: -0.0000

Data Index: 296123 (C4 (Web Text))

Max Activating Token Index: 828

Text #3

Max Range: 0.8051. Min Range: -0.8051

Max Act: 0.5872. Min Act: -0.0000

Data Index: 1439160 (Python Code)

Max Activating Token Index: 423

Text #4

Max Range: 0.8051. Min Range: -0.8051

Max Act: 0.6016. Min Act: -0.0000

Data Index: 571953 (C4 (Web Text))

Max Activating Token Index: 339

Text #5

Max Range: 0.8051. Min Range: -0.8051

Max Act: 0.6343. Min Act: -0.0000

Data Index: 127694 (C4 (Web Text))

Max Activating Token Index: 439

Text #6

Max Range: 0.8051. Min Range: -0.8051

Max Act: 0.5923. Min Act: -0.0000

Data Index: 292110 (C4 (Web Text))

Max Activating Token Index: 715

Text #7

Max Range: 0.8051. Min Range: -0.8051

Max Act: 0.5812. Min Act: -0.0000

Data Index: 1575753 (Python Code)

Max Activating Token Index: 318

Text #8

Max Range: 0.8051. Min Range: -0.8051

Max Act: 0.6253. Min Act: -0.0000

Data Index: 505114 (C4 (Web Text))

Max Activating Token Index: 278

Text #9

Max Range: 0.8051. Min Range: -0.8051

Max Act: 0.5954. Min Act: -0.0000

Data Index: 1309820 (C4 (Web Text))

Max Activating Token Index: 235

Text #10

Max Range: 0.8051. Min Range: -0.8051

Max Act: 0.5908. Min Act: -0.0000

Data Index: 104599 (C4 (Web Text))

Max Activating Token Index: 291

Text #11

Max Range: 0.8051. Min Range: -0.8051

Max Act: 0.5857. Min Act: -0.0000

Data Index: 603618 (C4 (Web Text))

Max Activating Token Index: 92

Text #12

Max Range: 0.8051. Min Range: -0.8051

Max Act: 0.5647. Min Act: -0.0000

Data Index: 344141 (C4 (Web Text))

Max Activating Token Index: 20

Text #13

Max Range: 0.8051. Min Range: -0.8051

Max Act: 0.5921. Min Act: -0.0000

Data Index: 922066 (C4 (Web Text))

Max Activating Token Index: 865

Text #14

Max Range: 0.8051. Min Range: -0.8051

Max Act: 0.5714. Min Act: -0.0000

Data Index: 665301 (C4 (Web Text))

Max Activating Token Index: 552

Text #15

Max Range: 0.8051. Min Range: -0.8051

Max Act: 0.5845. Min Act: -0.0000

Data Index: 141061 (C4 (Web Text))

Max Activating Token Index: 84

Text #16

Max Range: 0.8051. Min Range: -0.8051

Max Act: 0.5699. Min Act: -0.0000

Data Index: 345920 (C4 (Web Text))

Max Activating Token Index: 403

Text #17

Max Range: 0.8051. Min Range: -0.8051

Max Act: 0.5709. Min Act: -0.0000

Data Index: 681374 (C4 (Web Text))

Max Activating Token Index: 388

Text #18

Max Range: 0.8051. Min Range: -0.8051

Max Act: 0.5509. Min Act: -0.0000

Data Index: 654660 (C4 (Web Text))

Max Activating Token Index: 435

Text #19

Max Range: 0.8051. Min Range: -0.8051

Max Act: 0.5755. Min Act: -0.0000

Data Index: 1273687 (C4 (Web Text))

Max Activating Token Index: 626