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

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

Neuron 654 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3974. Min Range: -0.3974

Max Act: 0.3974. Min Act: -0.0001

Data Index: 689504 (C4 (Web Text))

Max Activating Token Index: 888

Text #1

Max Range: 0.3974. Min Range: -0.3974

Max Act: 0.3620. Min Act: -0.0000

Data Index: 145820 (C4 (Web Text))

Max Activating Token Index: 144

Text #2

Max Range: 0.3974. Min Range: -0.3974

Max Act: 0.3505. Min Act: -0.0000

Data Index: 828627 (C4 (Web Text))

Max Activating Token Index: 693

Text #3

Max Range: 0.3974. Min Range: -0.3974

Max Act: 0.3288. Min Act: -0.0001

Data Index: 355911 (C4 (Web Text))

Max Activating Token Index: 794

Text #4

Max Range: 0.3974. Min Range: -0.3974

Max Act: 0.3265. Min Act: -0.0000

Data Index: 1296355 (C4 (Web Text))

Max Activating Token Index: 116

Text #5

Max Range: 0.3974. Min Range: -0.3974

Max Act: 0.3230. Min Act: -0.0001

Data Index: 1075146 (C4 (Web Text))

Max Activating Token Index: 821

Text #6

Max Range: 0.3974. Min Range: -0.3974

Max Act: 0.3082. Min Act: -0.0001

Data Index: 1106727 (C4 (Web Text))

Max Activating Token Index: 275

Text #7

Max Range: 0.3974. Min Range: -0.3974

Max Act: 0.3313. Min Act: -0.0001

Data Index: 750670 (C4 (Web Text))

Max Activating Token Index: 393

Text #8

Max Range: 0.3974. Min Range: -0.3974

Max Act: 0.3063. Min Act: -0.0001

Data Index: 1232007 (C4 (Web Text))

Max Activating Token Index: 717

Text #9

Max Range: 0.3974. Min Range: -0.3974

Max Act: 0.2804. Min Act: -0.0000

Data Index: 279755 (C4 (Web Text))

Max Activating Token Index: 154

Text #10

Max Range: 0.3974. Min Range: -0.3974

Max Act: 0.2756. Min Act: -0.0000

Data Index: 795888 (C4 (Web Text))

Max Activating Token Index: 429

Text #11

Max Range: 0.3974. Min Range: -0.3974

Max Act: 0.2734. Min Act: -0.0000

Data Index: 654652 (C4 (Web Text))

Max Activating Token Index: 509

Text #12

Max Range: 0.3974. Min Range: -0.3974

Max Act: 0.2673. Min Act: -0.0001

Data Index: 738088 (C4 (Web Text))

Max Activating Token Index: 294

Text #13

Max Range: 0.3974. Min Range: -0.3974

Max Act: 0.2603. Min Act: -0.0001

Data Index: 269908 (C4 (Web Text))

Max Activating Token Index: 872

Text #14

Max Range: 0.3974. Min Range: -0.3974

Max Act: 0.2498. Min Act: -0.0000

Data Index: 641432 (C4 (Web Text))

Max Activating Token Index: 89

Text #15

Max Range: 0.3974. Min Range: -0.3974

Max Act: 0.2588. Min Act: -0.0000

Data Index: 1035153 (C4 (Web Text))

Max Activating Token Index: 976

Text #16

Max Range: 0.3974. Min Range: -0.3974

Max Act: 0.2534. Min Act: -0.0001

Data Index: 530137 (C4 (Web Text))

Max Activating Token Index: 993

Text #17

Max Range: 0.3974. Min Range: -0.3974

Max Act: 0.2600. Min Act: -0.0000

Data Index: 988797 (C4 (Web Text))

Max Activating Token Index: 78

Text #18

Max Range: 0.3974. Min Range: -0.3974

Max Act: 0.2394. Min Act: -0.0000

Data Index: 739171 (C4 (Web Text))

Max Activating Token Index: 847

Text #19

Max Range: 0.3974. Min Range: -0.3974

Max Act: 0.2660. Min Act: -0.0001

Data Index: 694339 (C4 (Web Text))

Max Activating Token Index: 718