Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2706 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 2.0600. Min Range: -2.0600

Max Act: 2.0600. Min Act: -0.0001

Data Index: 10768 (C4 (Web Text))

Max Activating Token Index: 110

Text #1

Max Range: 2.0600. Min Range: -2.0600

Max Act: 1.7357. Min Act: -0.0001

Data Index: 60731 (C4 (Web Text))

Max Activating Token Index: 310

Text #2

Max Range: 2.0600. Min Range: -2.0600

Max Act: 1.7975. Min Act: -0.0001

Data Index: 1367295 (Python Code)

Max Activating Token Index: 268

Text #3

Max Range: 2.0600. Min Range: -2.0600

Max Act: 1.7954. Min Act: -0.0001

Data Index: 70874 (C4 (Web Text))

Max Activating Token Index: 209

Text #4

Max Range: 2.0600. Min Range: -2.0600

Max Act: 1.6495. Min Act: -0.0001

Data Index: 602228 (C4 (Web Text))

Max Activating Token Index: 323

Text #5

Max Range: 2.0600. Min Range: -2.0600

Max Act: 1.6692. Min Act: -0.0000

Data Index: 1303566 (C4 (Web Text))

Max Activating Token Index: 184

Text #6

Max Range: 2.0600. Min Range: -2.0600

Max Act: 1.6048. Min Act: -0.0001

Data Index: 766185 (C4 (Web Text))

Max Activating Token Index: 648

Text #7

Max Range: 2.0600. Min Range: -2.0600

Max Act: 1.5081. Min Act: -0.0000

Data Index: 1104347 (C4 (Web Text))

Max Activating Token Index: 520

Text #8

Max Range: 2.0600. Min Range: -2.0600

Max Act: 1.5487. Min Act: -0.0001

Data Index: 824226 (C4 (Web Text))

Max Activating Token Index: 881

Text #9

Max Range: 2.0600. Min Range: -2.0600

Max Act: 1.5978. Min Act: -0.0001

Data Index: 405514 (C4 (Web Text))

Max Activating Token Index: 53

Text #10

Max Range: 2.0600. Min Range: -2.0600

Max Act: 1.5182. Min Act: -0.0000

Data Index: 772076 (C4 (Web Text))

Max Activating Token Index: 752

Text #11

Max Range: 2.0600. Min Range: -2.0600

Max Act: 1.4574. Min Act: -0.0001

Data Index: 501478 (C4 (Web Text))

Max Activating Token Index: 631

Text #12

Max Range: 2.0600. Min Range: -2.0600

Max Act: 1.5626. Min Act: -0.0001

Data Index: 614331 (C4 (Web Text))

Max Activating Token Index: 547

Text #13

Max Range: 2.0600. Min Range: -2.0600

Max Act: 1.5682. Min Act: -0.0000

Data Index: 1150026 (C4 (Web Text))

Max Activating Token Index: 232

Text #14

Max Range: 2.0600. Min Range: -2.0600

Max Act: 1.5011. Min Act: -0.0000

Data Index: 664560 (C4 (Web Text))

Max Activating Token Index: 247

Text #15

Max Range: 2.0600. Min Range: -2.0600

Max Act: 1.5445. Min Act: -0.0001

Data Index: 1162336 (C4 (Web Text))

Max Activating Token Index: 665

Text #16

Max Range: 2.0600. Min Range: -2.0600

Max Act: 1.4688. Min Act: -0.0000

Data Index: 690165 (C4 (Web Text))

Max Activating Token Index: 543

Text #17

Max Range: 2.0600. Min Range: -2.0600

Max Act: 1.5206. Min Act: -0.0001

Data Index: 746265 (C4 (Web Text))

Max Activating Token Index: 885

Text #18

Max Range: 2.0600. Min Range: -2.0600

Max Act: 1.5144. Min Act: -0.0000

Data Index: 1212669 (C4 (Web Text))

Max Activating Token Index: 157

Text #19

Max Range: 2.0600. Min Range: -2.0600

Max Act: 1.5435. Min Act: -0.0000

Data Index: 982748 (C4 (Web Text))

Max Activating Token Index: 632