Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 3783 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0520. Min Act: -0.0000

Data Index: 1426766 (The Pile)

Max Activating Token Index: 1023

Text #1

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0501. Min Act: -0.0000

Data Index: 690394 (The Pile)

Max Activating Token Index: 1023

Text #2

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0502. Min Act: 0.0000

Data Index: 670648 (The Pile)

Max Activating Token Index: 1023

Text #3

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0495. Min Act: -0.0000

Data Index: 2528 (The Pile)

Max Activating Token Index: 13

Text #4

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0491. Min Act: -0.0000

Data Index: 185062 (The Pile)

Max Activating Token Index: 1023

Text #5

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0477. Min Act: -0.0000

Data Index: 1832046 (The Pile)

Max Activating Token Index: 14

Text #6

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0493. Min Act: -0.0000

Data Index: 793590 (The Pile)

Max Activating Token Index: 1023

Text #7

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0474. Min Act: -0.0000

Data Index: 243629 (The Pile)

Max Activating Token Index: 1023

Text #8

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0471. Min Act: -0.0000

Data Index: 1691118 (The Pile)

Max Activating Token Index: 1023

Text #9

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0470. Min Act: 0.0000

Data Index: 992312 (The Pile)

Max Activating Token Index: 1023

Text #10

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0469. Min Act: -0.0000

Data Index: 556191 (The Pile)

Max Activating Token Index: 1023

Text #11

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0464. Min Act: 0.0000

Data Index: 34570 (The Pile)

Max Activating Token Index: 1023

Text #12

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0460. Min Act: -0.0000

Data Index: 1827506 (The Pile)

Max Activating Token Index: 1023

Text #13

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0458. Min Act: -0.0000

Data Index: 1669607 (The Pile)

Max Activating Token Index: 998

Text #14

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0450. Min Act: -0.0000

Data Index: 926602 (The Pile)

Max Activating Token Index: 1011

Text #15

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0455. Min Act: -0.0000

Data Index: 1292362 (The Pile)

Max Activating Token Index: 1023

Text #16

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0454. Min Act: -0.0000

Data Index: 1267093 (The Pile)

Max Activating Token Index: 964

Text #17

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0454. Min Act: -0.0000

Data Index: 1453510 (The Pile)

Max Activating Token Index: 1023

Text #18

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0453. Min Act: -0.0000

Data Index: 1478587 (The Pile)

Max Activating Token Index: 981

Text #19

Max Range: 0.0520. Min Range: -0.0520

Max Act: 0.0452. Min Act: -0.0000

Data Index: 1914140 (The Pile)

Max Activating Token Index: 1023