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

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

Neuron 186 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: 0.7376. Min Range: -0.7376

Max Act: 0.7376. Min Act: -0.0000

Data Index: 1239193 (C4 (Web Text))

Max Activating Token Index: 56

Text #1

Max Range: 0.7376. Min Range: -0.7376

Max Act: 0.6911. Min Act: -0.0000

Data Index: 1238161 (C4 (Web Text))

Max Activating Token Index: 861

Text #2

Max Range: 0.7376. Min Range: -0.7376

Max Act: 0.5822. Min Act: -0.0000

Data Index: 504939 (C4 (Web Text))

Max Activating Token Index: 525

Text #3

Max Range: 0.7376. Min Range: -0.7376

Max Act: 0.5676. Min Act: -0.0000

Data Index: 1242501 (C4 (Web Text))

Max Activating Token Index: 49

Text #4

Max Range: 0.7376. Min Range: -0.7376

Max Act: 0.5470. Min Act: -0.0001

Data Index: 735596 (C4 (Web Text))

Max Activating Token Index: 203

Text #5

Max Range: 0.7376. Min Range: -0.7376

Max Act: 0.5027. Min Act: -0.0001

Data Index: 605831 (C4 (Web Text))

Max Activating Token Index: 60

Text #6

Max Range: 0.7376. Min Range: -0.7376

Max Act: 0.5414. Min Act: -0.0001

Data Index: 1089063 (C4 (Web Text))

Max Activating Token Index: 537

Text #7

Max Range: 0.7376. Min Range: -0.7376

Max Act: 0.5333. Min Act: -0.0000

Data Index: 1285587 (C4 (Web Text))

Max Activating Token Index: 158

Text #8

Max Range: 0.7376. Min Range: -0.7376

Max Act: 0.5224. Min Act: -0.0001

Data Index: 148966 (C4 (Web Text))

Max Activating Token Index: 892

Text #9

Max Range: 0.7376. Min Range: -0.7376

Max Act: 0.4550. Min Act: -0.0000

Data Index: 873695 (C4 (Web Text))

Max Activating Token Index: 305

Text #10

Max Range: 0.7376. Min Range: -0.7376

Max Act: 0.4969. Min Act: -0.0001

Data Index: 314387 (C4 (Web Text))

Max Activating Token Index: 20

Text #11

Max Range: 0.7376. Min Range: -0.7376

Max Act: 0.4564. Min Act: -0.0001

Data Index: 129669 (C4 (Web Text))

Max Activating Token Index: 820

Text #12

Max Range: 0.7376. Min Range: -0.7376

Max Act: 0.4754. Min Act: -0.0000

Data Index: 834587 (C4 (Web Text))

Max Activating Token Index: 443

Text #13

Max Range: 0.7376. Min Range: -0.7376

Max Act: 0.4705. Min Act: -0.0000

Data Index: 15639 (C4 (Web Text))

Max Activating Token Index: 398

Text #14

Max Range: 0.7376. Min Range: -0.7376

Max Act: 0.4969. Min Act: -0.0000

Data Index: 548536 (C4 (Web Text))

Max Activating Token Index: 771

Text #15

Max Range: 0.7376. Min Range: -0.7376

Max Act: 0.4321. Min Act: -0.0000

Data Index: 94257 (C4 (Web Text))

Max Activating Token Index: 611

Text #16

Max Range: 0.7376. Min Range: -0.7376

Max Act: 0.5063. Min Act: -0.0000

Data Index: 1270035 (C4 (Web Text))

Max Activating Token Index: 463

Text #17

Max Range: 0.7376. Min Range: -0.7376

Max Act: 0.4434. Min Act: -0.0000

Data Index: 1035983 (C4 (Web Text))

Max Activating Token Index: 419

Text #18

Max Range: 0.7376. Min Range: -0.7376

Max Act: 0.4542. Min Act: -0.0000

Data Index: 53478 (C4 (Web Text))

Max Activating Token Index: 470

Text #19

Max Range: 0.7376. Min Range: -0.7376

Max Act: 0.3739. Min Act: -0.0000

Data Index: 881807 (C4 (Web Text))

Max Activating Token Index: 198