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

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

Neuron 3528 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2439. Min Range: -2.2439

Max Act: 2.2439. Min Act: -0.0000

Data Index: 644586 (C4 (Web Text))

Max Activating Token Index: 903

Text #1

Max Range: 2.2439. Min Range: -2.2439

Max Act: 1.7444. Min Act: -0.0000

Data Index: 428319 (C4 (Web Text))

Max Activating Token Index: 72

Text #2

Max Range: 2.2439. Min Range: -2.2439

Max Act: 1.5055. Min Act: -0.0000

Data Index: 1324463 (C4 (Web Text))

Max Activating Token Index: 114

Text #3

Max Range: 2.2439. Min Range: -2.2439

Max Act: 1.5206. Min Act: -0.0000

Data Index: 202534 (C4 (Web Text))

Max Activating Token Index: 581

Text #4

Max Range: 2.2439. Min Range: -2.2439

Max Act: 1.5099. Min Act: -0.0000

Data Index: 927431 (C4 (Web Text))

Max Activating Token Index: 849

Text #5

Max Range: 2.2439. Min Range: -2.2439

Max Act: 1.4909. Min Act: -0.0000

Data Index: 190923 (C4 (Web Text))

Max Activating Token Index: 206

Text #6

Max Range: 2.2439. Min Range: -2.2439

Max Act: 1.6394. Min Act: -0.0000

Data Index: 373229 (C4 (Web Text))

Max Activating Token Index: 41

Text #7

Max Range: 2.2439. Min Range: -2.2439

Max Act: 1.5491. Min Act: -0.0000

Data Index: 152194 (C4 (Web Text))

Max Activating Token Index: 504

Text #8

Max Range: 2.2439. Min Range: -2.2439

Max Act: 1.3769. Min Act: -0.0000

Data Index: 861410 (C4 (Web Text))

Max Activating Token Index: 528

Text #9

Max Range: 2.2439. Min Range: -2.2439

Max Act: 1.4415. Min Act: -0.0000

Data Index: 750157 (C4 (Web Text))

Max Activating Token Index: 1008

Text #10

Max Range: 2.2439. Min Range: -2.2439

Max Act: 1.2444. Min Act: -0.0000

Data Index: 1284654 (C4 (Web Text))

Max Activating Token Index: 897

Text #11

Max Range: 2.2439. Min Range: -2.2439

Max Act: 1.3961. Min Act: -0.0000

Data Index: 99077 (C4 (Web Text))

Max Activating Token Index: 969

Text #12

Max Range: 2.2439. Min Range: -2.2439

Max Act: 1.4684. Min Act: -0.0000

Data Index: 1336300 (C4 (Web Text))

Max Activating Token Index: 984

Text #13

Max Range: 2.2439. Min Range: -2.2439

Max Act: 1.3132. Min Act: -0.0000

Data Index: 605737 (C4 (Web Text))

Max Activating Token Index: 959

Text #14

Max Range: 2.2439. Min Range: -2.2439

Max Act: 1.3024. Min Act: -0.0000

Data Index: 640440 (C4 (Web Text))

Max Activating Token Index: 466

Text #15

Max Range: 2.2439. Min Range: -2.2439

Max Act: 1.2057. Min Act: -0.0000

Data Index: 219439 (C4 (Web Text))

Max Activating Token Index: 134

Text #16

Max Range: 2.2439. Min Range: -2.2439

Max Act: 1.2733. Min Act: -0.0000

Data Index: 677356 (C4 (Web Text))

Max Activating Token Index: 1013

Text #17

Max Range: 2.2439. Min Range: -2.2439

Max Act: 1.2403. Min Act: -0.0000

Data Index: 1116646 (C4 (Web Text))

Max Activating Token Index: 29

Text #18

Max Range: 2.2439. Min Range: -2.2439

Max Act: 1.2736. Min Act: -0.0000

Data Index: 1127656 (C4 (Web Text))

Max Activating Token Index: 124

Text #19

Max Range: 2.2439. Min Range: -2.2439

Max Act: 1.2490. Min Act: -0.0000

Data Index: 1244554 (C4 (Web Text))

Max Activating Token Index: 220