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

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

Neuron 345 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3901. Min Range: -2.3901

Max Act: 2.3901. Min Act: -0.0000

Data Index: 1288872 (C4 (Web Text))

Max Activating Token Index: 12

Text #1

Max Range: 2.3901. Min Range: -2.3901

Max Act: 2.1810. Min Act: -0.0000

Data Index: 447706 (C4 (Web Text))

Max Activating Token Index: 506

Text #2

Max Range: 2.3901. Min Range: -2.3901

Max Act: 2.0696. Min Act: 0.0000

Data Index: 587912 (C4 (Web Text))

Max Activating Token Index: 95

Text #3

Max Range: 2.3901. Min Range: -2.3901

Max Act: 2.0797. Min Act: -0.0000

Data Index: 751767 (C4 (Web Text))

Max Activating Token Index: 139

Text #4

Max Range: 2.3901. Min Range: -2.3901

Max Act: 1.9795. Min Act: -0.0000

Data Index: 1497572 (Python Code)

Max Activating Token Index: 294

Text #5

Max Range: 2.3901. Min Range: -2.3901

Max Act: 1.8243. Min Act: -0.0000

Data Index: 1304128 (C4 (Web Text))

Max Activating Token Index: 286

Text #6

Max Range: 2.3901. Min Range: -2.3901

Max Act: 1.8702. Min Act: -0.0000

Data Index: 1447161 (Python Code)

Max Activating Token Index: 392

Text #7

Max Range: 2.3901. Min Range: -2.3901

Max Act: 1.7249. Min Act: -0.0000

Data Index: 515300 (C4 (Web Text))

Max Activating Token Index: 990

Text #8

Max Range: 2.3901. Min Range: -2.3901

Max Act: 1.8620. Min Act: -0.0000

Data Index: 1020926 (C4 (Web Text))

Max Activating Token Index: 326

Text #9

Max Range: 2.3901. Min Range: -2.3901

Max Act: 1.7547. Min Act: -0.0000

Data Index: 1490536 (Python Code)

Max Activating Token Index: 822

Text #10

Max Range: 2.3901. Min Range: -2.3901

Max Act: 1.7500. Min Act: -0.0000

Data Index: 1502386 (Python Code)

Max Activating Token Index: 184

Text #11

Max Range: 2.3901. Min Range: -2.3901

Max Act: 1.6866. Min Act: -0.0000

Data Index: 713687 (C4 (Web Text))

Max Activating Token Index: 931

Text #12

Max Range: 2.3901. Min Range: -2.3901

Max Act: 1.7923. Min Act: -0.0000

Data Index: 1486864 (Python Code)

Max Activating Token Index: 160

Text #13

Max Range: 2.3901. Min Range: -2.3901

Max Act: 1.6066. Min Act: -0.0000

Data Index: 139203 (C4 (Web Text))

Max Activating Token Index: 1017

Text #14

Max Range: 2.3901. Min Range: -2.3901

Max Act: 1.5942. Min Act: -0.0000

Data Index: 397620 (C4 (Web Text))

Max Activating Token Index: 701

Text #15

Max Range: 2.3901. Min Range: -2.3901

Max Act: 1.5000. Min Act: -0.0000

Data Index: 1439411 (Python Code)

Max Activating Token Index: 39

Text #16

Max Range: 2.3901. Min Range: -2.3901

Max Act: 1.7876. Min Act: -0.0000

Data Index: 160545 (C4 (Web Text))

Max Activating Token Index: 110

Text #17

Max Range: 2.3901. Min Range: -2.3901

Max Act: 1.5697. Min Act: -0.0000

Data Index: 142025 (C4 (Web Text))

Max Activating Token Index: 824

Text #18

Max Range: 2.3901. Min Range: -2.3901

Max Act: 1.6945. Min Act: -0.0000

Data Index: 230066 (C4 (Web Text))

Max Activating Token Index: 451

Text #19

Max Range: 2.3901. Min Range: -2.3901

Max Act: 1.5351. Min Act: -0.0000

Data Index: 862420 (C4 (Web Text))

Max Activating Token Index: 16