Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1217 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0476. Min Act: -0.0004

Data Index: 550064 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0437. Min Act: -0.0004

Data Index: 827690 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0445. Min Act: -0.0004

Data Index: 206521 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0406. Min Act: -0.0004

Data Index: 1267688 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0417. Min Act: -0.0004

Data Index: 1144115 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0381. Min Act: -0.0004

Data Index: 157122 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0340. Min Act: -0.0004

Data Index: 1456999 (Python Code)

Max Activating Token Index: 1023

Text #7

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0356. Min Act: -0.0004

Data Index: 602942 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0344. Min Act: -0.0004

Data Index: 780069 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0367. Min Act: -0.0004

Data Index: 959514 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0368. Min Act: -0.0004

Data Index: 688962 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0351. Min Act: -0.0004

Data Index: 1458190 (Python Code)

Max Activating Token Index: 1023

Text #12

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0364. Min Act: -0.0004

Data Index: 1255326 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0380. Min Act: -0.0004

Data Index: 1420631 (Python Code)

Max Activating Token Index: 1023

Text #14

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0334. Min Act: -0.0004

Data Index: 742092 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0336. Min Act: -0.0004

Data Index: 1248984 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0334. Min Act: -0.0004

Data Index: 1571187 (Python Code)

Max Activating Token Index: 1023

Text #17

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0330. Min Act: -0.0004

Data Index: 797869 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0330. Min Act: -0.0004

Data Index: 1332559 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0343. Min Act: -0.0004

Data Index: 1276510 (C4 (Web Text))

Max Activating Token Index: 1023