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

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

Neuron 4708 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: 1.5820. Min Range: -1.5820

Max Act: 1.5820. Min Act: -0.0000

Data Index: 761935 (C4 (Web Text))

Max Activating Token Index: 223

Text #1

Max Range: 1.5820. Min Range: -1.5820

Max Act: 1.4294. Min Act: -0.0000

Data Index: 765832 (C4 (Web Text))

Max Activating Token Index: 294

Text #2

Max Range: 1.5820. Min Range: -1.5820

Max Act: 1.1958. Min Act: -0.0000

Data Index: 443478 (C4 (Web Text))

Max Activating Token Index: 82

Text #3

Max Range: 1.5820. Min Range: -1.5820

Max Act: 1.2536. Min Act: -0.0000

Data Index: 827641 (C4 (Web Text))

Max Activating Token Index: 700

Text #4

Max Range: 1.5820. Min Range: -1.5820

Max Act: 1.2865. Min Act: -0.0000

Data Index: 961279 (C4 (Web Text))

Max Activating Token Index: 270

Text #5

Max Range: 1.5820. Min Range: -1.5820

Max Act: 1.1819. Min Act: -0.0000

Data Index: 337259 (C4 (Web Text))

Max Activating Token Index: 692

Text #6

Max Range: 1.5820. Min Range: -1.5820

Max Act: 1.0045. Min Act: -0.0000

Data Index: 1459000 (Python Code)

Max Activating Token Index: 776

Text #7

Max Range: 1.5820. Min Range: -1.5820

Max Act: 1.0377. Min Act: -0.0000

Data Index: 702935 (C4 (Web Text))

Max Activating Token Index: 39

Text #8

Max Range: 1.5820. Min Range: -1.5820

Max Act: 1.0949. Min Act: -0.0000

Data Index: 71052 (C4 (Web Text))

Max Activating Token Index: 200

Text #9

Max Range: 1.5820. Min Range: -1.5820

Max Act: 0.8677. Min Act: -0.0000

Data Index: 1285178 (C4 (Web Text))

Max Activating Token Index: 739

Text #10

Max Range: 1.5820. Min Range: -1.5820

Max Act: 0.9817. Min Act: -0.0000

Data Index: 186964 (C4 (Web Text))

Max Activating Token Index: 39

Text #11

Max Range: 1.5820. Min Range: -1.5820

Max Act: 0.9302. Min Act: 0.0000

Data Index: 98996 (C4 (Web Text))

Max Activating Token Index: 561

Text #12

Max Range: 1.5820. Min Range: -1.5820

Max Act: 0.9348. Min Act: -0.0000

Data Index: 1614924 (Python Code)

Max Activating Token Index: 206

Text #13

Max Range: 1.5820. Min Range: -1.5820

Max Act: 0.9361. Min Act: -0.0000

Data Index: 1222591 (C4 (Web Text))

Max Activating Token Index: 539

Text #14

Max Range: 1.5820. Min Range: -1.5820

Max Act: 0.8449. Min Act: -0.0000

Data Index: 1119098 (C4 (Web Text))

Max Activating Token Index: 683

Text #15

Max Range: 1.5820. Min Range: -1.5820

Max Act: 0.8492. Min Act: -0.0000

Data Index: 1582266 (Python Code)

Max Activating Token Index: 912

Text #16

Max Range: 1.5820. Min Range: -1.5820

Max Act: 0.8429. Min Act: -0.0000

Data Index: 951939 (C4 (Web Text))

Max Activating Token Index: 121

Text #17

Max Range: 1.5820. Min Range: -1.5820

Max Act: 0.8599. Min Act: -0.0000

Data Index: 1611984 (Python Code)

Max Activating Token Index: 851

Text #18

Max Range: 1.5820. Min Range: -1.5820

Max Act: 0.8336. Min Act: -0.0000

Data Index: 646167 (C4 (Web Text))

Max Activating Token Index: 60

Text #19

Max Range: 1.5820. Min Range: -1.5820

Max Act: 0.8377. Min Act: -0.0000

Data Index: 1091645 (C4 (Web Text))

Max Activating Token Index: 820