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

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

Neuron 5201 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7600. Min Range: -1.7600

Max Act: 1.7261. Min Act: -0.0000

Data Index: 1266971 (C4 (Web Text))

Max Activating Token Index: 646

Text #1

Max Range: 1.7600. Min Range: -1.7600

Max Act: 1.7600. Min Act: -0.0000

Data Index: 724245 (C4 (Web Text))

Max Activating Token Index: 4

Text #2

Max Range: 1.7600. Min Range: -1.7600

Max Act: 1.6714. Min Act: -0.0000

Data Index: 148174 (C4 (Web Text))

Max Activating Token Index: 550

Text #3

Max Range: 1.7600. Min Range: -1.7600

Max Act: 1.6570. Min Act: -0.0000

Data Index: 1100547 (C4 (Web Text))

Max Activating Token Index: 285

Text #4

Max Range: 1.7600. Min Range: -1.7600

Max Act: 1.6300. Min Act: -0.0000

Data Index: 211989 (C4 (Web Text))

Max Activating Token Index: 230

Text #5

Max Range: 1.7600. Min Range: -1.7600

Max Act: 1.4773. Min Act: -0.0000

Data Index: 69650 (C4 (Web Text))

Max Activating Token Index: 15

Text #6

Max Range: 1.7600. Min Range: -1.7600

Max Act: 1.5489. Min Act: -0.0000

Data Index: 546576 (C4 (Web Text))

Max Activating Token Index: 255

Text #7

Max Range: 1.7600. Min Range: -1.7600

Max Act: 1.4953. Min Act: -0.0000

Data Index: 508289 (C4 (Web Text))

Max Activating Token Index: 104

Text #8

Max Range: 1.7600. Min Range: -1.7600

Max Act: 1.3927. Min Act: -0.0000

Data Index: 824107 (C4 (Web Text))

Max Activating Token Index: 902

Text #9

Max Range: 1.7600. Min Range: -1.7600

Max Act: 1.4671. Min Act: -0.0000

Data Index: 433936 (C4 (Web Text))

Max Activating Token Index: 193

Text #10

Max Range: 1.7600. Min Range: -1.7600

Max Act: 1.3945. Min Act: -0.0000

Data Index: 761223 (C4 (Web Text))

Max Activating Token Index: 383

Text #11

Max Range: 1.7600. Min Range: -1.7600

Max Act: 1.3666. Min Act: -0.0000

Data Index: 1238470 (C4 (Web Text))

Max Activating Token Index: 54

Text #12

Max Range: 1.7600. Min Range: -1.7600

Max Act: 1.3583. Min Act: -0.0000

Data Index: 1090142 (C4 (Web Text))

Max Activating Token Index: 525

Text #13

Max Range: 1.7600. Min Range: -1.7600

Max Act: 1.2747. Min Act: -0.0000

Data Index: 368621 (C4 (Web Text))

Max Activating Token Index: 392

Text #14

Max Range: 1.7600. Min Range: -1.7600

Max Act: 1.4136. Min Act: -0.0000

Data Index: 916353 (C4 (Web Text))

Max Activating Token Index: 282

Text #15

Max Range: 1.7600. Min Range: -1.7600

Max Act: 1.3320. Min Act: -0.0000

Data Index: 1146809 (C4 (Web Text))

Max Activating Token Index: 329

Text #16

Max Range: 1.7600. Min Range: -1.7600

Max Act: 1.4014. Min Act: -0.0000

Data Index: 564975 (C4 (Web Text))

Max Activating Token Index: 112

Text #17

Max Range: 1.7600. Min Range: -1.7600

Max Act: 1.2838. Min Act: -0.0000

Data Index: 959307 (C4 (Web Text))

Max Activating Token Index: 606

Text #18

Max Range: 1.7600. Min Range: -1.7600

Max Act: 1.2314. Min Act: -0.0000

Data Index: 1446864 (Python Code)

Max Activating Token Index: 14

Text #19

Max Range: 1.7600. Min Range: -1.7600

Max Act: 1.2576. Min Act: -0.0000

Data Index: 79922 (C4 (Web Text))

Max Activating Token Index: 344