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

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

Neuron 576 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0035. Min Range: -3.0035

Max Act: 3.0035. Min Act: -0.0002

Data Index: 650168 (C4 (Web Text))

Max Activating Token Index: 555

Text #1

Max Range: 3.0035. Min Range: -3.0035

Max Act: 2.0970. Min Act: -0.0002

Data Index: 1171433 (C4 (Web Text))

Max Activating Token Index: 929

Text #2

Max Range: 3.0035. Min Range: -3.0035

Max Act: 2.0641. Min Act: -0.0002

Data Index: 1078530 (C4 (Web Text))

Max Activating Token Index: 109

Text #3

Max Range: 3.0035. Min Range: -3.0035

Max Act: 1.9823. Min Act: -0.0001

Data Index: 1109242 (C4 (Web Text))

Max Activating Token Index: 138

Text #4

Max Range: 3.0035. Min Range: -3.0035

Max Act: 1.8738. Min Act: -0.0001

Data Index: 768447 (C4 (Web Text))

Max Activating Token Index: 446

Text #5

Max Range: 3.0035. Min Range: -3.0035

Max Act: 1.8391. Min Act: -0.0002

Data Index: 1313128 (C4 (Web Text))

Max Activating Token Index: 36

Text #6

Max Range: 3.0035. Min Range: -3.0035

Max Act: 1.7907. Min Act: -0.0001

Data Index: 880255 (C4 (Web Text))

Max Activating Token Index: 16

Text #7

Max Range: 3.0035. Min Range: -3.0035

Max Act: 1.7438. Min Act: -0.0002

Data Index: 46714 (C4 (Web Text))

Max Activating Token Index: 342

Text #8

Max Range: 3.0035. Min Range: -3.0035

Max Act: 1.8370. Min Act: -0.0002

Data Index: 1012617 (C4 (Web Text))

Max Activating Token Index: 206

Text #9

Max Range: 3.0035. Min Range: -3.0035

Max Act: 1.7150. Min Act: -0.0001

Data Index: 1158538 (C4 (Web Text))

Max Activating Token Index: 581

Text #10

Max Range: 3.0035. Min Range: -3.0035

Max Act: 1.6427. Min Act: -0.0002

Data Index: 341672 (C4 (Web Text))

Max Activating Token Index: 756

Text #11

Max Range: 3.0035. Min Range: -3.0035

Max Act: 1.6846. Min Act: -0.0001

Data Index: 1137042 (C4 (Web Text))

Max Activating Token Index: 659

Text #12

Max Range: 3.0035. Min Range: -3.0035

Max Act: 1.6341. Min Act: -0.0002

Data Index: 358015 (C4 (Web Text))

Max Activating Token Index: 335

Text #13

Max Range: 3.0035. Min Range: -3.0035

Max Act: 1.5813. Min Act: -0.0002

Data Index: 1118572 (C4 (Web Text))

Max Activating Token Index: 360

Text #14

Max Range: 3.0035. Min Range: -3.0035

Max Act: 1.6701. Min Act: -0.0002

Data Index: 424988 (C4 (Web Text))

Max Activating Token Index: 942

Text #15

Max Range: 3.0035. Min Range: -3.0035

Max Act: 1.6086. Min Act: -0.0002

Data Index: 265307 (C4 (Web Text))

Max Activating Token Index: 337

Text #16

Max Range: 3.0035. Min Range: -3.0035

Max Act: 1.6548. Min Act: -0.0001

Data Index: 1248935 (C4 (Web Text))

Max Activating Token Index: 864

Text #17

Max Range: 3.0035. Min Range: -3.0035

Max Act: 1.5954. Min Act: -0.0002

Data Index: 224061 (C4 (Web Text))

Max Activating Token Index: 245

Text #18

Max Range: 3.0035. Min Range: -3.0035

Max Act: 1.5851. Min Act: -0.0001

Data Index: 261399 (C4 (Web Text))

Max Activating Token Index: 28

Text #19

Max Range: 3.0035. Min Range: -3.0035

Max Act: 1.6839. Min Act: -0.0002

Data Index: 115952 (C4 (Web Text))

Max Activating Token Index: 774