Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2378 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.7607. Min Range: -0.7607

Max Act: 0.7607. Min Act: -0.0001

Data Index: 227844 (C4 (Web Text))

Max Activating Token Index: 90

Text #1

Max Range: 0.7607. Min Range: -0.7607

Max Act: 0.6465. Min Act: -0.0001

Data Index: 740283 (C4 (Web Text))

Max Activating Token Index: 559

Text #2

Max Range: 0.7607. Min Range: -0.7607

Max Act: 0.5839. Min Act: -0.0001

Data Index: 705954 (C4 (Web Text))

Max Activating Token Index: 468

Text #3

Max Range: 0.7607. Min Range: -0.7607

Max Act: 0.5577. Min Act: -0.0001

Data Index: 619069 (C4 (Web Text))

Max Activating Token Index: 169

Text #4

Max Range: 0.7607. Min Range: -0.7607

Max Act: 0.5546. Min Act: -0.0001

Data Index: 36135 (C4 (Web Text))

Max Activating Token Index: 264

Text #5

Max Range: 0.7607. Min Range: -0.7607

Max Act: 0.5495. Min Act: -0.0001

Data Index: 1122048 (C4 (Web Text))

Max Activating Token Index: 614

Text #6

Max Range: 0.7607. Min Range: -0.7607

Max Act: 0.5494. Min Act: -0.0001

Data Index: 33184 (C4 (Web Text))

Max Activating Token Index: 620

Text #7

Max Range: 0.7607. Min Range: -0.7607

Max Act: 0.5291. Min Act: -0.0000

Data Index: 539652 (C4 (Web Text))

Max Activating Token Index: 529

Text #8

Max Range: 0.7607. Min Range: -0.7607

Max Act: 0.5605. Min Act: -0.0001

Data Index: 294054 (C4 (Web Text))

Max Activating Token Index: 749

Text #9

Max Range: 0.7607. Min Range: -0.7607

Max Act: 0.5625. Min Act: -0.0001

Data Index: 1034385 (C4 (Web Text))

Max Activating Token Index: 993

Text #10

Max Range: 0.7607. Min Range: -0.7607

Max Act: 0.5362. Min Act: -0.0001

Data Index: 685884 (C4 (Web Text))

Max Activating Token Index: 217

Text #11

Max Range: 0.7607. Min Range: -0.7607

Max Act: 0.5324. Min Act: -0.0001

Data Index: 478660 (C4 (Web Text))

Max Activating Token Index: 432

Text #12

Max Range: 0.7607. Min Range: -0.7607

Max Act: 0.5339. Min Act: 0.0001

Data Index: 150046 (C4 (Web Text))

Max Activating Token Index: 144

Text #13

Max Range: 0.7607. Min Range: -0.7607

Max Act: 0.5234. Min Act: -0.0001

Data Index: 415594 (C4 (Web Text))

Max Activating Token Index: 578

Text #14

Max Range: 0.7607. Min Range: -0.7607

Max Act: 0.5117. Min Act: -0.0001

Data Index: 930804 (C4 (Web Text))

Max Activating Token Index: 901

Text #15

Max Range: 0.7607. Min Range: -0.7607

Max Act: 0.5162. Min Act: -0.0001

Data Index: 133373 (C4 (Web Text))

Max Activating Token Index: 844

Text #16

Max Range: 0.7607. Min Range: -0.7607

Max Act: 0.4937. Min Act: -0.0001

Data Index: 412517 (C4 (Web Text))

Max Activating Token Index: 1006

Text #17

Max Range: 0.7607. Min Range: -0.7607

Max Act: 0.5118. Min Act: -0.0001

Data Index: 114162 (C4 (Web Text))

Max Activating Token Index: 649

Text #18

Max Range: 0.7607. Min Range: -0.7607

Max Act: 0.5066. Min Act: -0.0001

Data Index: 721009 (C4 (Web Text))

Max Activating Token Index: 145

Text #19

Max Range: 0.7607. Min Range: -0.7607

Max Act: 0.4995. Min Act: -0.0001

Data Index: 1232819 (C4 (Web Text))

Max Activating Token Index: 738