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

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

Neuron 1347 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6792. Min Range: -1.6792

Max Act: 1.6792. Min Act: -0.0001

Data Index: 262922 (C4 (Web Text))

Max Activating Token Index: 835

Text #1

Max Range: 1.6792. Min Range: -1.6792

Max Act: 1.4311. Min Act: -0.0001

Data Index: 531264 (C4 (Web Text))

Max Activating Token Index: 71

Text #2

Max Range: 1.6792. Min Range: -1.6792

Max Act: 1.5136. Min Act: -0.0001

Data Index: 1371737 (Python Code)

Max Activating Token Index: 160

Text #3

Max Range: 1.6792. Min Range: -1.6792

Max Act: 1.5109. Min Act: -0.0001

Data Index: 168205 (C4 (Web Text))

Max Activating Token Index: 129

Text #4

Max Range: 1.6792. Min Range: -1.6792

Max Act: 1.3299. Min Act: -0.0001

Data Index: 436605 (C4 (Web Text))

Max Activating Token Index: 769

Text #5

Max Range: 1.6792. Min Range: -1.6792

Max Act: 1.4089. Min Act: -0.0001

Data Index: 645471 (C4 (Web Text))

Max Activating Token Index: 644

Text #6

Max Range: 1.6792. Min Range: -1.6792

Max Act: 1.2771. Min Act: -0.0001

Data Index: 274447 (C4 (Web Text))

Max Activating Token Index: 964

Text #7

Max Range: 1.6792. Min Range: -1.6792

Max Act: 1.4352. Min Act: -0.0001

Data Index: 223179 (C4 (Web Text))

Max Activating Token Index: 523

Text #8

Max Range: 1.6792. Min Range: -1.6792

Max Act: 1.3510. Min Act: -0.0001

Data Index: 1421039 (Python Code)

Max Activating Token Index: 871

Text #9

Max Range: 1.6792. Min Range: -1.6792

Max Act: 1.3693. Min Act: -0.0001

Data Index: 1232048 (C4 (Web Text))

Max Activating Token Index: 834

Text #10

Max Range: 1.6792. Min Range: -1.6792

Max Act: 1.3963. Min Act: -0.0001

Data Index: 1084515 (C4 (Web Text))

Max Activating Token Index: 845

Text #11

Max Range: 1.6792. Min Range: -1.6792

Max Act: 1.3443. Min Act: -0.0001

Data Index: 1108003 (C4 (Web Text))

Max Activating Token Index: 649

Text #12

Max Range: 1.6792. Min Range: -1.6792

Max Act: 1.2354. Min Act: -0.0001

Data Index: 259628 (C4 (Web Text))

Max Activating Token Index: 738

Text #13

Max Range: 1.6792. Min Range: -1.6792

Max Act: 1.3049. Min Act: -0.0001

Data Index: 153442 (C4 (Web Text))

Max Activating Token Index: 48

Text #14

Max Range: 1.6792. Min Range: -1.6792

Max Act: 1.3362. Min Act: -0.0001

Data Index: 343771 (C4 (Web Text))

Max Activating Token Index: 822

Text #15

Max Range: 1.6792. Min Range: -1.6792

Max Act: 1.3357. Min Act: -0.0001

Data Index: 1641788 (Python Code)

Max Activating Token Index: 363

Text #16

Max Range: 1.6792. Min Range: -1.6792

Max Act: 1.3184. Min Act: -0.0001

Data Index: 102428 (C4 (Web Text))

Max Activating Token Index: 7

Text #17

Max Range: 1.6792. Min Range: -1.6792

Max Act: 1.2327. Min Act: -0.0001

Data Index: 171272 (C4 (Web Text))

Max Activating Token Index: 896

Text #18

Max Range: 1.6792. Min Range: -1.6792

Max Act: 1.3209. Min Act: -0.0001

Data Index: 59778 (C4 (Web Text))

Max Activating Token Index: 856

Text #19

Max Range: 1.6792. Min Range: -1.6792

Max Act: 1.2132. Min Act: -0.0001

Data Index: 567621 (C4 (Web Text))

Max Activating Token Index: 255