Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1623 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.5708. Min Range: -1.5708

Max Act: 1.5708. Min Act: -0.0000

Data Index: 398994 (C4 (Web Text))

Max Activating Token Index: 8

Text #1

Max Range: 1.5708. Min Range: -1.5708

Max Act: 1.4481. Min Act: -0.0000

Data Index: 739650 (C4 (Web Text))

Max Activating Token Index: 9

Text #2

Max Range: 1.5708. Min Range: -1.5708

Max Act: 1.3486. Min Act: -0.0001

Data Index: 996358 (C4 (Web Text))

Max Activating Token Index: 8

Text #3

Max Range: 1.5708. Min Range: -1.5708

Max Act: 1.2513. Min Act: -0.0000

Data Index: 665662 (C4 (Web Text))

Max Activating Token Index: 16

Text #4

Max Range: 1.5708. Min Range: -1.5708

Max Act: 1.2082. Min Act: -0.0000

Data Index: 401519 (C4 (Web Text))

Max Activating Token Index: 403

Text #5

Max Range: 1.5708. Min Range: -1.5708

Max Act: 1.2228. Min Act: -0.0000

Data Index: 1084872 (C4 (Web Text))

Max Activating Token Index: 8

Text #6

Max Range: 1.5708. Min Range: -1.5708

Max Act: 1.1185. Min Act: -0.0001

Data Index: 889514 (C4 (Web Text))

Max Activating Token Index: 875

Text #7

Max Range: 1.5708. Min Range: -1.5708

Max Act: 1.0912. Min Act: -0.0000

Data Index: 123751 (C4 (Web Text))

Max Activating Token Index: 21

Text #8

Max Range: 1.5708. Min Range: -1.5708

Max Act: 1.1184. Min Act: -0.0000

Data Index: 771120 (C4 (Web Text))

Max Activating Token Index: 387

Text #9

Max Range: 1.5708. Min Range: -1.5708

Max Act: 1.0529. Min Act: -0.0000

Data Index: 1008683 (C4 (Web Text))

Max Activating Token Index: 73

Text #10

Max Range: 1.5708. Min Range: -1.5708

Max Act: 1.1070. Min Act: -0.0000

Data Index: 512673 (C4 (Web Text))

Max Activating Token Index: 474

Text #11

Max Range: 1.5708. Min Range: -1.5708

Max Act: 1.1082. Min Act: -0.0000

Data Index: 1114666 (C4 (Web Text))

Max Activating Token Index: 122

Text #12

Max Range: 1.5708. Min Range: -1.5708

Max Act: 1.0425. Min Act: -0.0000

Data Index: 821792 (C4 (Web Text))

Max Activating Token Index: 188

Text #13

Max Range: 1.5708. Min Range: -1.5708

Max Act: 1.0349. Min Act: -0.0000

Data Index: 626005 (C4 (Web Text))

Max Activating Token Index: 7

Text #14

Max Range: 1.5708. Min Range: -1.5708

Max Act: 0.9956. Min Act: -0.0000

Data Index: 369732 (C4 (Web Text))

Max Activating Token Index: 235

Text #15

Max Range: 1.5708. Min Range: -1.5708

Max Act: 1.0387. Min Act: -0.0000

Data Index: 1099724 (C4 (Web Text))

Max Activating Token Index: 14

Text #16

Max Range: 1.5708. Min Range: -1.5708

Max Act: 1.0260. Min Act: -0.0000

Data Index: 198802 (C4 (Web Text))

Max Activating Token Index: 42

Text #17

Max Range: 1.5708. Min Range: -1.5708

Max Act: 1.0250. Min Act: -0.0000

Data Index: 263726 (C4 (Web Text))

Max Activating Token Index: 695

Text #18

Max Range: 1.5708. Min Range: -1.5708

Max Act: 1.0485. Min Act: -0.0000

Data Index: 1279434 (C4 (Web Text))

Max Activating Token Index: 81

Text #19

Max Range: 1.5708. Min Range: -1.5708

Max Act: 1.0243. Min Act: -0.0001

Data Index: 624731 (C4 (Web Text))

Max Activating Token Index: 1013