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

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

Neuron 5677 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.7036. Min Range: -0.7036

Max Act: 0.7036. Min Act: -0.0000

Data Index: 393570 (C4 (Web Text))

Max Activating Token Index: 425

Text #1

Max Range: 0.7036. Min Range: -0.7036

Max Act: 0.6691. Min Act: -0.0000

Data Index: 786327 (C4 (Web Text))

Max Activating Token Index: 375

Text #2

Max Range: 0.7036. Min Range: -0.7036

Max Act: 0.5946. Min Act: -0.0000

Data Index: 844288 (C4 (Web Text))

Max Activating Token Index: 763

Text #3

Max Range: 0.7036. Min Range: -0.7036

Max Act: 0.5746. Min Act: -0.0000

Data Index: 405093 (C4 (Web Text))

Max Activating Token Index: 155

Text #4

Max Range: 0.7036. Min Range: -0.7036

Max Act: 0.5541. Min Act: -0.0000

Data Index: 77508 (C4 (Web Text))

Max Activating Token Index: 591

Text #5

Max Range: 0.7036. Min Range: -0.7036

Max Act: 0.5724. Min Act: -0.0000

Data Index: 1306247 (C4 (Web Text))

Max Activating Token Index: 96

Text #6

Max Range: 0.7036. Min Range: -0.7036

Max Act: 0.5439. Min Act: -0.0000

Data Index: 1045228 (C4 (Web Text))

Max Activating Token Index: 961

Text #7

Max Range: 0.7036. Min Range: -0.7036

Max Act: 0.5903. Min Act: -0.0000

Data Index: 461503 (C4 (Web Text))

Max Activating Token Index: 521

Text #8

Max Range: 0.7036. Min Range: -0.7036

Max Act: 0.5899. Min Act: -0.0000

Data Index: 1118279 (C4 (Web Text))

Max Activating Token Index: 432

Text #9

Max Range: 0.7036. Min Range: -0.7036

Max Act: 0.5676. Min Act: -0.0000

Data Index: 877889 (C4 (Web Text))

Max Activating Token Index: 412

Text #10

Max Range: 0.7036. Min Range: -0.7036

Max Act: 0.5135. Min Act: -0.0000

Data Index: 391012 (C4 (Web Text))

Max Activating Token Index: 545

Text #11

Max Range: 0.7036. Min Range: -0.7036

Max Act: 0.5259. Min Act: -0.0000

Data Index: 927316 (C4 (Web Text))

Max Activating Token Index: 360

Text #12

Max Range: 0.7036. Min Range: -0.7036

Max Act: 0.5647. Min Act: -0.0000

Data Index: 1206483 (C4 (Web Text))

Max Activating Token Index: 203

Text #13

Max Range: 0.7036. Min Range: -0.7036

Max Act: 0.5407. Min Act: -0.0000

Data Index: 905336 (C4 (Web Text))

Max Activating Token Index: 494

Text #14

Max Range: 0.7036. Min Range: -0.7036

Max Act: 0.4913. Min Act: -0.0000

Data Index: 349502 (C4 (Web Text))

Max Activating Token Index: 671

Text #15

Max Range: 0.7036. Min Range: -0.7036

Max Act: 0.4522. Min Act: -0.0000

Data Index: 893029 (C4 (Web Text))

Max Activating Token Index: 803

Text #16

Max Range: 0.7036. Min Range: -0.7036

Max Act: 0.4365. Min Act: -0.0000

Data Index: 347651 (C4 (Web Text))

Max Activating Token Index: 593

Text #17

Max Range: 0.7036. Min Range: -0.7036

Max Act: 0.4255. Min Act: -0.0000

Data Index: 163725 (C4 (Web Text))

Max Activating Token Index: 145

Text #18

Max Range: 0.7036. Min Range: -0.7036

Max Act: 0.4193. Min Act: -0.0000

Data Index: 1255438 (C4 (Web Text))

Max Activating Token Index: 1007

Text #19

Max Range: 0.7036. Min Range: -0.7036

Max Act: 0.3802. Min Act: -0.0000

Data Index: 749495 (C4 (Web Text))

Max Activating Token Index: 403