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

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

Neuron 4112 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.9122. Min Range: -4.9122

Max Act: 4.9122. Min Act: -0.0000

Data Index: 265463 (C4 (Web Text))

Max Activating Token Index: 409

Text #1

Max Range: 4.9122. Min Range: -4.9122

Max Act: 3.9335. Min Act: -0.0000

Data Index: 1018210 (C4 (Web Text))

Max Activating Token Index: 889

Text #2

Max Range: 4.9122. Min Range: -4.9122

Max Act: 3.7911. Min Act: -0.0000

Data Index: 712480 (C4 (Web Text))

Max Activating Token Index: 551

Text #3

Max Range: 4.9122. Min Range: -4.9122

Max Act: 3.5650. Min Act: -0.0000

Data Index: 405603 (C4 (Web Text))

Max Activating Token Index: 16

Text #4

Max Range: 4.9122. Min Range: -4.9122

Max Act: 3.2974. Min Act: -0.0000

Data Index: 693892 (C4 (Web Text))

Max Activating Token Index: 546

Text #5

Max Range: 4.9122. Min Range: -4.9122

Max Act: 3.2946. Min Act: -0.0000

Data Index: 589336 (C4 (Web Text))

Max Activating Token Index: 558

Text #6

Max Range: 4.9122. Min Range: -4.9122

Max Act: 3.2731. Min Act: -0.0000

Data Index: 239340 (C4 (Web Text))

Max Activating Token Index: 237

Text #7

Max Range: 4.9122. Min Range: -4.9122

Max Act: 2.9795. Min Act: -0.0000

Data Index: 1200737 (C4 (Web Text))

Max Activating Token Index: 357

Text #8

Max Range: 4.9122. Min Range: -4.9122

Max Act: 3.1656. Min Act: -0.0000

Data Index: 1137349 (C4 (Web Text))

Max Activating Token Index: 5

Text #9

Max Range: 4.9122. Min Range: -4.9122

Max Act: 3.1593. Min Act: -0.0000

Data Index: 409177 (C4 (Web Text))

Max Activating Token Index: 413

Text #10

Max Range: 4.9122. Min Range: -4.9122

Max Act: 3.1370. Min Act: -0.0000

Data Index: 1273536 (C4 (Web Text))

Max Activating Token Index: 224

Text #11

Max Range: 4.9122. Min Range: -4.9122

Max Act: 2.9405. Min Act: -0.0000

Data Index: 580498 (C4 (Web Text))

Max Activating Token Index: 356

Text #12

Max Range: 4.9122. Min Range: -4.9122

Max Act: 2.9438. Min Act: -0.0000

Data Index: 182889 (C4 (Web Text))

Max Activating Token Index: 370

Text #13

Max Range: 4.9122. Min Range: -4.9122

Max Act: 2.9836. Min Act: -0.0000

Data Index: 208893 (C4 (Web Text))

Max Activating Token Index: 913

Text #14

Max Range: 4.9122. Min Range: -4.9122

Max Act: 3.0065. Min Act: -0.0000

Data Index: 1273150 (C4 (Web Text))

Max Activating Token Index: 246

Text #15

Max Range: 4.9122. Min Range: -4.9122

Max Act: 2.8572. Min Act: -0.0000

Data Index: 248212 (C4 (Web Text))

Max Activating Token Index: 737

Text #16

Max Range: 4.9122. Min Range: -4.9122

Max Act: 2.6753. Min Act: -0.0000

Data Index: 603317 (C4 (Web Text))

Max Activating Token Index: 296

Text #17

Max Range: 4.9122. Min Range: -4.9122

Max Act: 2.9350. Min Act: -0.0000

Data Index: 228034 (C4 (Web Text))

Max Activating Token Index: 557

Text #18

Max Range: 4.9122. Min Range: -4.9122

Max Act: 2.7809. Min Act: -0.0000

Data Index: 29431 (C4 (Web Text))

Max Activating Token Index: 116

Text #19

Max Range: 4.9122. Min Range: -4.9122

Max Act: 2.5071. Min Act: -0.0000

Data Index: 42448 (C4 (Web Text))

Max Activating Token Index: 898