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

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

Neuron 561 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: 3.2293. Min Range: -3.2293

Max Act: 3.2293. Min Act: -0.0000

Data Index: 1147407 (C4 (Web Text))

Max Activating Token Index: 831

Text #1

Max Range: 3.2293. Min Range: -3.2293

Max Act: 2.8131. Min Act: -0.0000

Data Index: 1025839 (C4 (Web Text))

Max Activating Token Index: 640

Text #2

Max Range: 3.2293. Min Range: -3.2293

Max Act: 2.9221. Min Act: -0.0000

Data Index: 1146936 (C4 (Web Text))

Max Activating Token Index: 1014

Text #3

Max Range: 3.2293. Min Range: -3.2293

Max Act: 2.7869. Min Act: -0.0000

Data Index: 713755 (C4 (Web Text))

Max Activating Token Index: 60

Text #4

Max Range: 3.2293. Min Range: -3.2293

Max Act: 2.7957. Min Act: -0.0000

Data Index: 464970 (C4 (Web Text))

Max Activating Token Index: 996

Text #5

Max Range: 3.2293. Min Range: -3.2293

Max Act: 3.0695. Min Act: -0.0000

Data Index: 618670 (C4 (Web Text))

Max Activating Token Index: 339

Text #6

Max Range: 3.2293. Min Range: -3.2293

Max Act: 2.9387. Min Act: -0.0000

Data Index: 53644 (C4 (Web Text))

Max Activating Token Index: 612

Text #7

Max Range: 3.2293. Min Range: -3.2293

Max Act: 2.7844. Min Act: -0.0000

Data Index: 942675 (C4 (Web Text))

Max Activating Token Index: 153

Text #8

Max Range: 3.2293. Min Range: -3.2293

Max Act: 2.7960. Min Act: -0.0000

Data Index: 591985 (C4 (Web Text))

Max Activating Token Index: 43

Text #9

Max Range: 3.2293. Min Range: -3.2293

Max Act: 2.5295. Min Act: -0.0000

Data Index: 462436 (C4 (Web Text))

Max Activating Token Index: 271

Text #10

Max Range: 3.2293. Min Range: -3.2293

Max Act: 2.8515. Min Act: -0.0000

Data Index: 705463 (C4 (Web Text))

Max Activating Token Index: 105

Text #11

Max Range: 3.2293. Min Range: -3.2293

Max Act: 2.6893. Min Act: -0.0000

Data Index: 147180 (C4 (Web Text))

Max Activating Token Index: 574

Text #12

Max Range: 3.2293. Min Range: -3.2293

Max Act: 2.6922. Min Act: -0.0000

Data Index: 356414 (C4 (Web Text))

Max Activating Token Index: 89

Text #13

Max Range: 3.2293. Min Range: -3.2293

Max Act: 2.5579. Min Act: -0.0000

Data Index: 86660 (C4 (Web Text))

Max Activating Token Index: 1015

Text #14

Max Range: 3.2293. Min Range: -3.2293

Max Act: 2.6754. Min Act: -0.0000

Data Index: 1094417 (C4 (Web Text))

Max Activating Token Index: 573

Text #15

Max Range: 3.2293. Min Range: -3.2293

Max Act: 2.6585. Min Act: -0.0000

Data Index: 964804 (C4 (Web Text))

Max Activating Token Index: 204

Text #16

Max Range: 3.2293. Min Range: -3.2293

Max Act: 2.9294. Min Act: -0.0000

Data Index: 463650 (C4 (Web Text))

Max Activating Token Index: 145

Text #17

Max Range: 3.2293. Min Range: -3.2293

Max Act: 2.6813. Min Act: -0.0000

Data Index: 82820 (C4 (Web Text))

Max Activating Token Index: 954

Text #18

Max Range: 3.2293. Min Range: -3.2293

Max Act: 2.6875. Min Act: -0.0000

Data Index: 6708 (C4 (Web Text))

Max Activating Token Index: 1001

Text #19

Max Range: 3.2293. Min Range: -3.2293

Max Act: 2.8114. Min Act: -0.0000

Data Index: 170612 (C4 (Web Text))

Max Activating Token Index: 863