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

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

Neuron 4038 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1551. Min Range: -2.1551

Max Act: 2.1551. Min Act: -0.0000

Data Index: 891571 (C4 (Web Text))

Max Activating Token Index: 269

Text #1

Max Range: 2.1551. Min Range: -2.1551

Max Act: 2.1509. Min Act: -0.0001

Data Index: 740772 (C4 (Web Text))

Max Activating Token Index: 5

Text #2

Max Range: 2.1551. Min Range: -2.1551

Max Act: 2.0066. Min Act: -0.0001

Data Index: 1294070 (C4 (Web Text))

Max Activating Token Index: 518

Text #3

Max Range: 2.1551. Min Range: -2.1551

Max Act: 1.8979. Min Act: 0.0000

Data Index: 489871 (C4 (Web Text))

Max Activating Token Index: 143

Text #4

Max Range: 2.1551. Min Range: -2.1551

Max Act: 1.8993. Min Act: -0.0000

Data Index: 270249 (C4 (Web Text))

Max Activating Token Index: 466

Text #5

Max Range: 2.1551. Min Range: -2.1551

Max Act: 1.8283. Min Act: 0.0002

Data Index: 589640 (C4 (Web Text))

Max Activating Token Index: 96

Text #6

Max Range: 2.1551. Min Range: -2.1551

Max Act: 1.7545. Min Act: -0.0000

Data Index: 747492 (C4 (Web Text))

Max Activating Token Index: 839

Text #7

Max Range: 2.1551. Min Range: -2.1551

Max Act: 1.7928. Min Act: -0.0000

Data Index: 1250665 (C4 (Web Text))

Max Activating Token Index: 543

Text #8

Max Range: 2.1551. Min Range: -2.1551

Max Act: 1.6939. Min Act: -0.0001

Data Index: 1167752 (C4 (Web Text))

Max Activating Token Index: 128

Text #9

Max Range: 2.1551. Min Range: -2.1551

Max Act: 1.8916. Min Act: -0.0000

Data Index: 1267938 (C4 (Web Text))

Max Activating Token Index: 60

Text #10

Max Range: 2.1551. Min Range: -2.1551

Max Act: 1.7953. Min Act: -0.0000

Data Index: 1298824 (C4 (Web Text))

Max Activating Token Index: 207

Text #11

Max Range: 2.1551. Min Range: -2.1551

Max Act: 1.7056. Min Act: -0.0001

Data Index: 1268323 (C4 (Web Text))

Max Activating Token Index: 926

Text #12

Max Range: 2.1551. Min Range: -2.1551

Max Act: 1.5929. Min Act: -0.0001

Data Index: 957346 (C4 (Web Text))

Max Activating Token Index: 11

Text #13

Max Range: 2.1551. Min Range: -2.1551

Max Act: 1.6124. Min Act: -0.0000

Data Index: 536897 (C4 (Web Text))

Max Activating Token Index: 17

Text #14

Max Range: 2.1551. Min Range: -2.1551

Max Act: 1.7598. Min Act: -0.0000

Data Index: 22827 (C4 (Web Text))

Max Activating Token Index: 149

Text #15

Max Range: 2.1551. Min Range: -2.1551

Max Act: 1.6070. Min Act: -0.0000

Data Index: 604529 (C4 (Web Text))

Max Activating Token Index: 242

Text #16

Max Range: 2.1551. Min Range: -2.1551

Max Act: 1.7061. Min Act: -0.0000

Data Index: 95368 (C4 (Web Text))

Max Activating Token Index: 903

Text #17

Max Range: 2.1551. Min Range: -2.1551

Max Act: 1.4482. Min Act: -0.0001

Data Index: 883992 (C4 (Web Text))

Max Activating Token Index: 42

Text #18

Max Range: 2.1551. Min Range: -2.1551

Max Act: 1.4499. Min Act: -0.0000

Data Index: 504060 (C4 (Web Text))

Max Activating Token Index: 524

Text #19

Max Range: 2.1551. Min Range: -2.1551

Max Act: 1.5484. Min Act: -0.0000

Data Index: 472598 (C4 (Web Text))

Max Activating Token Index: 40