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

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

Neuron 3045 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7424. Min Range: -0.7424

Max Act: 0.7123. Min Act: -0.0000

Data Index: 989077 (C4 (Web Text))

Max Activating Token Index: 33

Text #1

Max Range: 0.7424. Min Range: -0.7424

Max Act: 0.7296. Min Act: -0.0000

Data Index: 126009 (C4 (Web Text))

Max Activating Token Index: 549

Text #2

Max Range: 0.7424. Min Range: -0.7424

Max Act: 0.7424. Min Act: -0.0000

Data Index: 347361 (C4 (Web Text))

Max Activating Token Index: 739

Text #3

Max Range: 0.7424. Min Range: -0.7424

Max Act: 0.6226. Min Act: -0.0001

Data Index: 1315985 (C4 (Web Text))

Max Activating Token Index: 975

Text #4

Max Range: 0.7424. Min Range: -0.7424

Max Act: 0.6355. Min Act: -0.0000

Data Index: 58688 (C4 (Web Text))

Max Activating Token Index: 955

Text #5

Max Range: 0.7424. Min Range: -0.7424

Max Act: 0.5317. Min Act: -0.0000

Data Index: 830646 (C4 (Web Text))

Max Activating Token Index: 866

Text #6

Max Range: 0.7424. Min Range: -0.7424

Max Act: 0.6163. Min Act: -0.0001

Data Index: 642755 (C4 (Web Text))

Max Activating Token Index: 842

Text #7

Max Range: 0.7424. Min Range: -0.7424

Max Act: 0.5732. Min Act: -0.0001

Data Index: 261476 (C4 (Web Text))

Max Activating Token Index: 965

Text #8

Max Range: 0.7424. Min Range: -0.7424

Max Act: 0.5097. Min Act: -0.0000

Data Index: 650322 (C4 (Web Text))

Max Activating Token Index: 57

Text #9

Max Range: 0.7424. Min Range: -0.7424

Max Act: 0.4812. Min Act: -0.0001

Data Index: 907796 (C4 (Web Text))

Max Activating Token Index: 842

Text #10

Max Range: 0.7424. Min Range: -0.7424

Max Act: 0.5095. Min Act: -0.0000

Data Index: 865993 (C4 (Web Text))

Max Activating Token Index: 63

Text #11

Max Range: 0.7424. Min Range: -0.7424

Max Act: 0.5050. Min Act: -0.0000

Data Index: 655634 (C4 (Web Text))

Max Activating Token Index: 602

Text #12

Max Range: 0.7424. Min Range: -0.7424

Max Act: 0.5116. Min Act: -0.0000

Data Index: 244881 (C4 (Web Text))

Max Activating Token Index: 869

Text #13

Max Range: 0.7424. Min Range: -0.7424

Max Act: 0.4472. Min Act: -0.0000

Data Index: 133681 (C4 (Web Text))

Max Activating Token Index: 292

Text #14

Max Range: 0.7424. Min Range: -0.7424

Max Act: 0.4881. Min Act: -0.0001

Data Index: 260696 (C4 (Web Text))

Max Activating Token Index: 215

Text #15

Max Range: 0.7424. Min Range: -0.7424

Max Act: 0.4812. Min Act: -0.0000

Data Index: 888413 (C4 (Web Text))

Max Activating Token Index: 797

Text #16

Max Range: 0.7424. Min Range: -0.7424

Max Act: 0.4696. Min Act: -0.0001

Data Index: 628395 (C4 (Web Text))

Max Activating Token Index: 823

Text #17

Max Range: 0.7424. Min Range: -0.7424

Max Act: 0.5021. Min Act: -0.0000

Data Index: 1518251 (Python Code)

Max Activating Token Index: 48

Text #18

Max Range: 0.7424. Min Range: -0.7424

Max Act: 0.4653. Min Act: -0.0000

Data Index: 238024 (C4 (Web Text))

Max Activating Token Index: 76

Text #19

Max Range: 0.7424. Min Range: -0.7424

Max Act: 0.5101. Min Act: -0.0000

Data Index: 256040 (C4 (Web Text))

Max Activating Token Index: 316