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

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

Neuron 826 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1019. Min Range: -1.1019

Max Act: 1.1019. Min Act: -0.0001

Data Index: 489260 (C4 (Web Text))

Max Activating Token Index: 657

Text #1

Max Range: 1.1019. Min Range: -1.1019

Max Act: 0.7122. Min Act: -0.0001

Data Index: 191473 (C4 (Web Text))

Max Activating Token Index: 26

Text #2

Max Range: 1.1019. Min Range: -1.1019

Max Act: 0.6897. Min Act: -0.0001

Data Index: 818508 (C4 (Web Text))

Max Activating Token Index: 603

Text #3

Max Range: 1.1019. Min Range: -1.1019

Max Act: 0.6686. Min Act: -0.0001

Data Index: 461501 (C4 (Web Text))

Max Activating Token Index: 664

Text #4

Max Range: 1.1019. Min Range: -1.1019

Max Act: 0.7276. Min Act: -0.0001

Data Index: 316976 (C4 (Web Text))

Max Activating Token Index: 840

Text #5

Max Range: 1.1019. Min Range: -1.1019

Max Act: 0.6910. Min Act: -0.0001

Data Index: 577025 (C4 (Web Text))

Max Activating Token Index: 270

Text #6

Max Range: 1.1019. Min Range: -1.1019

Max Act: 0.6932. Min Act: -0.0001

Data Index: 440612 (C4 (Web Text))

Max Activating Token Index: 389

Text #7

Max Range: 1.1019. Min Range: -1.1019

Max Act: 0.6443. Min Act: -0.0001

Data Index: 383080 (C4 (Web Text))

Max Activating Token Index: 692

Text #8

Max Range: 1.1019. Min Range: -1.1019

Max Act: 0.6229. Min Act: -0.0001

Data Index: 951681 (C4 (Web Text))

Max Activating Token Index: 823

Text #9

Max Range: 1.1019. Min Range: -1.1019

Max Act: 0.6747. Min Act: -0.0001

Data Index: 274644 (C4 (Web Text))

Max Activating Token Index: 516

Text #10

Max Range: 1.1019. Min Range: -1.1019

Max Act: 0.5879. Min Act: -0.0001

Data Index: 84426 (C4 (Web Text))

Max Activating Token Index: 854

Text #11

Max Range: 1.1019. Min Range: -1.1019

Max Act: 0.5960. Min Act: -0.0001

Data Index: 799789 (C4 (Web Text))

Max Activating Token Index: 752

Text #12

Max Range: 1.1019. Min Range: -1.1019

Max Act: 0.6000. Min Act: -0.0001

Data Index: 826055 (C4 (Web Text))

Max Activating Token Index: 581

Text #13

Max Range: 1.1019. Min Range: -1.1019

Max Act: 0.6076. Min Act: -0.0001

Data Index: 959764 (C4 (Web Text))

Max Activating Token Index: 64

Text #14

Max Range: 1.1019. Min Range: -1.1019

Max Act: 0.5918. Min Act: -0.0001

Data Index: 1156444 (C4 (Web Text))

Max Activating Token Index: 303

Text #15

Max Range: 1.1019. Min Range: -1.1019

Max Act: 0.6429. Min Act: -0.0001

Data Index: 483549 (C4 (Web Text))

Max Activating Token Index: 888

Text #16

Max Range: 1.1019. Min Range: -1.1019

Max Act: 0.6166. Min Act: -0.0001

Data Index: 962452 (C4 (Web Text))

Max Activating Token Index: 647

Text #17

Max Range: 1.1019. Min Range: -1.1019

Max Act: 0.5350. Min Act: -0.0001

Data Index: 171398 (C4 (Web Text))

Max Activating Token Index: 799

Text #18

Max Range: 1.1019. Min Range: -1.1019

Max Act: 0.6227. Min Act: -0.0001

Data Index: 359317 (C4 (Web Text))

Max Activating Token Index: 76

Text #19

Max Range: 1.1019. Min Range: -1.1019

Max Act: 0.5577. Min Act: -0.0001

Data Index: 466364 (C4 (Web Text))

Max Activating Token Index: 978