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

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

Neuron 168 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0673. Min Range: -1.0673

Max Act: 1.0673. Min Act: -0.0000

Data Index: 441112 (C4 (Web Text))

Max Activating Token Index: 333

Text #1

Max Range: 1.0673. Min Range: -1.0673

Max Act: 0.9679. Min Act: -0.0000

Data Index: 1204436 (C4 (Web Text))

Max Activating Token Index: 435

Text #2

Max Range: 1.0673. Min Range: -1.0673

Max Act: 0.8502. Min Act: -0.0000

Data Index: 125738 (C4 (Web Text))

Max Activating Token Index: 421

Text #3

Max Range: 1.0673. Min Range: -1.0673

Max Act: 0.7808. Min Act: -0.0001

Data Index: 1547658 (Python Code)

Max Activating Token Index: 70

Text #4

Max Range: 1.0673. Min Range: -1.0673

Max Act: 0.8085. Min Act: -0.0000

Data Index: 887978 (C4 (Web Text))

Max Activating Token Index: 683

Text #5

Max Range: 1.0673. Min Range: -1.0673

Max Act: 0.7589. Min Act: -0.0000

Data Index: 1298170 (C4 (Web Text))

Max Activating Token Index: 63

Text #6

Max Range: 1.0673. Min Range: -1.0673

Max Act: 0.7296. Min Act: -0.0001

Data Index: 1550489 (Python Code)

Max Activating Token Index: 848

Text #7

Max Range: 1.0673. Min Range: -1.0673

Max Act: 0.7070. Min Act: -0.0001

Data Index: 1651037 (Python Code)

Max Activating Token Index: 92

Text #8

Max Range: 1.0673. Min Range: -1.0673

Max Act: 0.7530. Min Act: -0.0000

Data Index: 275582 (C4 (Web Text))

Max Activating Token Index: 540

Text #9

Max Range: 1.0673. Min Range: -1.0673

Max Act: 0.6964. Min Act: -0.0001

Data Index: 300073 (C4 (Web Text))

Max Activating Token Index: 161

Text #10

Max Range: 1.0673. Min Range: -1.0673

Max Act: 0.7159. Min Act: -0.0000

Data Index: 1037929 (C4 (Web Text))

Max Activating Token Index: 694

Text #11

Max Range: 1.0673. Min Range: -1.0673

Max Act: 0.6570. Min Act: -0.0000

Data Index: 147260 (C4 (Web Text))

Max Activating Token Index: 625

Text #12

Max Range: 1.0673. Min Range: -1.0673

Max Act: 0.6766. Min Act: -0.0000

Data Index: 166993 (C4 (Web Text))

Max Activating Token Index: 301

Text #13

Max Range: 1.0673. Min Range: -1.0673

Max Act: 0.6324. Min Act: -0.0000

Data Index: 1199096 (C4 (Web Text))

Max Activating Token Index: 862

Text #14

Max Range: 1.0673. Min Range: -1.0673

Max Act: 0.6506. Min Act: -0.0001

Data Index: 396471 (C4 (Web Text))

Max Activating Token Index: 175

Text #15

Max Range: 1.0673. Min Range: -1.0673

Max Act: 0.6464. Min Act: -0.0001

Data Index: 405091 (C4 (Web Text))

Max Activating Token Index: 454

Text #16

Max Range: 1.0673. Min Range: -1.0673

Max Act: 0.7067. Min Act: -0.0000

Data Index: 259423 (C4 (Web Text))

Max Activating Token Index: 723

Text #17

Max Range: 1.0673. Min Range: -1.0673

Max Act: 0.6388. Min Act: -0.0000

Data Index: 872497 (C4 (Web Text))

Max Activating Token Index: 583

Text #18

Max Range: 1.0673. Min Range: -1.0673

Max Act: 0.6348. Min Act: -0.0000

Data Index: 1180779 (C4 (Web Text))

Max Activating Token Index: 671

Text #19

Max Range: 1.0673. Min Range: -1.0673

Max Act: 0.6326. Min Act: -0.0001

Data Index: 1539067 (Python Code)

Max Activating Token Index: 851