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

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

Neuron 4359 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: 1.4300. Min Range: -1.4300

Max Act: 1.1535. Min Act: -0.0001

Data Index: 1025859 (C4 (Web Text))

Max Activating Token Index: 845

Text #1

Max Range: 1.4300. Min Range: -1.4300

Max Act: 1.3768. Min Act: -0.0000

Data Index: 376899 (C4 (Web Text))

Max Activating Token Index: 236

Text #2

Max Range: 1.4300. Min Range: -1.4300

Max Act: 1.4300. Min Act: -0.0000

Data Index: 1219987 (C4 (Web Text))

Max Activating Token Index: 505

Text #3

Max Range: 1.4300. Min Range: -1.4300

Max Act: 1.3223. Min Act: -0.0000

Data Index: 619785 (C4 (Web Text))

Max Activating Token Index: 427

Text #4

Max Range: 1.4300. Min Range: -1.4300

Max Act: 1.3078. Min Act: -0.0001

Data Index: 1277669 (C4 (Web Text))

Max Activating Token Index: 97

Text #5

Max Range: 1.4300. Min Range: -1.4300

Max Act: 1.2654. Min Act: -0.0001

Data Index: 205794 (C4 (Web Text))

Max Activating Token Index: 271

Text #6

Max Range: 1.4300. Min Range: -1.4300

Max Act: 1.3702. Min Act: -0.0000

Data Index: 1638425 (Python Code)

Max Activating Token Index: 49

Text #7

Max Range: 1.4300. Min Range: -1.4300

Max Act: 1.2925. Min Act: -0.0001

Data Index: 68095 (C4 (Web Text))

Max Activating Token Index: 330

Text #8

Max Range: 1.4300. Min Range: -1.4300

Max Act: 1.3072. Min Act: -0.0000

Data Index: 553135 (C4 (Web Text))

Max Activating Token Index: 429

Text #9

Max Range: 1.4300. Min Range: -1.4300

Max Act: 1.1967. Min Act: -0.0000

Data Index: 1321415 (C4 (Web Text))

Max Activating Token Index: 234

Text #10

Max Range: 1.4300. Min Range: -1.4300

Max Act: 1.3103. Min Act: -0.0001

Data Index: 620312 (C4 (Web Text))

Max Activating Token Index: 547

Text #11

Max Range: 1.4300. Min Range: -1.4300

Max Act: 1.1623. Min Act: -0.0001

Data Index: 516728 (C4 (Web Text))

Max Activating Token Index: 133

Text #12

Max Range: 1.4300. Min Range: -1.4300

Max Act: 1.3846. Min Act: -0.0000

Data Index: 519817 (C4 (Web Text))

Max Activating Token Index: 536

Text #13

Max Range: 1.4300. Min Range: -1.4300

Max Act: 1.1785. Min Act: -0.0000

Data Index: 1103246 (C4 (Web Text))

Max Activating Token Index: 149

Text #14

Max Range: 1.4300. Min Range: -1.4300

Max Act: 1.1787. Min Act: -0.0000

Data Index: 868506 (C4 (Web Text))

Max Activating Token Index: 586

Text #15

Max Range: 1.4300. Min Range: -1.4300

Max Act: 1.3595. Min Act: -0.0000

Data Index: 387199 (C4 (Web Text))

Max Activating Token Index: 737

Text #16

Max Range: 1.4300. Min Range: -1.4300

Max Act: 1.2765. Min Act: -0.0001

Data Index: 111542 (C4 (Web Text))

Max Activating Token Index: 435

Text #17

Max Range: 1.4300. Min Range: -1.4300

Max Act: 1.1929. Min Act: -0.0001

Data Index: 1250769 (C4 (Web Text))

Max Activating Token Index: 965

Text #18

Max Range: 1.4300. Min Range: -1.4300

Max Act: 1.1720. Min Act: -0.0000

Data Index: 1127058 (C4 (Web Text))

Max Activating Token Index: 117

Text #19

Max Range: 1.4300. Min Range: -1.4300

Max Act: 1.0653. Min Act: -0.0001

Data Index: 126585 (C4 (Web Text))

Max Activating Token Index: 674