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

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

Neuron 3715 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.0649. Min Range: -6.0649

Max Act: 5.7531. Min Act: -0.0000

Data Index: 1602258 (Python Code)

Max Activating Token Index: 401

Text #1

Max Range: 6.0649. Min Range: -6.0649

Max Act: 5.5460. Min Act: -0.0000

Data Index: 1641714 (Python Code)

Max Activating Token Index: 276

Text #2

Max Range: 6.0649. Min Range: -6.0649

Max Act: 5.9419. Min Act: -0.0000

Data Index: 1499789 (Python Code)

Max Activating Token Index: 970

Text #3

Max Range: 6.0649. Min Range: -6.0649

Max Act: 5.7792. Min Act: -0.0000

Data Index: 1450110 (Python Code)

Max Activating Token Index: 111

Text #4

Max Range: 6.0649. Min Range: -6.0649

Max Act: 6.0649. Min Act: -0.0000

Data Index: 1576488 (Python Code)

Max Activating Token Index: 431

Text #5

Max Range: 6.0649. Min Range: -6.0649

Max Act: 5.5738. Min Act: -0.0000

Data Index: 1502560 (Python Code)

Max Activating Token Index: 931

Text #6

Max Range: 6.0649. Min Range: -6.0649

Max Act: 5.6684. Min Act: -0.0000

Data Index: 1614178 (Python Code)

Max Activating Token Index: 58

Text #7

Max Range: 6.0649. Min Range: -6.0649

Max Act: 5.5377. Min Act: -0.0000

Data Index: 1624967 (Python Code)

Max Activating Token Index: 468

Text #8

Max Range: 6.0649. Min Range: -6.0649

Max Act: 5.2883. Min Act: -0.0000

Data Index: 1625369 (Python Code)

Max Activating Token Index: 502

Text #9

Max Range: 6.0649. Min Range: -6.0649

Max Act: 5.4683. Min Act: -0.0000

Data Index: 1556945 (Python Code)

Max Activating Token Index: 50

Text #10

Max Range: 6.0649. Min Range: -6.0649

Max Act: 5.4078. Min Act: -0.0000

Data Index: 1373679 (Python Code)

Max Activating Token Index: 59

Text #11

Max Range: 6.0649. Min Range: -6.0649

Max Act: 5.5534. Min Act: -0.0000

Data Index: 1574591 (Python Code)

Max Activating Token Index: 154

Text #12

Max Range: 6.0649. Min Range: -6.0649

Max Act: 5.1502. Min Act: -0.0000

Data Index: 1406784 (Python Code)

Max Activating Token Index: 98

Text #13

Max Range: 6.0649. Min Range: -6.0649

Max Act: 4.8853. Min Act: -0.0000

Data Index: 1625070 (Python Code)

Max Activating Token Index: 46

Text #14

Max Range: 6.0649. Min Range: -6.0649

Max Act: 4.9820. Min Act: -0.0001

Data Index: 1549376 (Python Code)

Max Activating Token Index: 211

Text #15

Max Range: 6.0649. Min Range: -6.0649

Max Act: 5.0792. Min Act: -0.0000

Data Index: 1459923 (Python Code)

Max Activating Token Index: 243

Text #16

Max Range: 6.0649. Min Range: -6.0649

Max Act: 4.8405. Min Act: -0.0000

Data Index: 1641992 (Python Code)

Max Activating Token Index: 23

Text #17

Max Range: 6.0649. Min Range: -6.0649

Max Act: 5.0060. Min Act: -0.0000

Data Index: 1371061 (Python Code)

Max Activating Token Index: 535

Text #18

Max Range: 6.0649. Min Range: -6.0649

Max Act: 4.7933. Min Act: -0.0000

Data Index: 1512864 (Python Code)

Max Activating Token Index: 11

Text #19

Max Range: 6.0649. Min Range: -6.0649

Max Act: 4.5677. Min Act: -0.0000

Data Index: 1541454 (Python Code)

Max Activating Token Index: 529