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

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

Neuron 1547 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: 0.1645. Min Range: -0.1645

Max Act: 0.1645. Min Act: -0.0001

Data Index: 247474 (C4 (Web Text))

Max Activating Token Index: 83

Text #1

Max Range: 0.1645. Min Range: -0.1645

Max Act: 0.1440. Min Act: -0.0001

Data Index: 803227 (C4 (Web Text))

Max Activating Token Index: 535

Text #2

Max Range: 0.1645. Min Range: -0.1645

Max Act: 0.1525. Min Act: -0.0001

Data Index: 351415 (C4 (Web Text))

Max Activating Token Index: 969

Text #3

Max Range: 0.1645. Min Range: -0.1645

Max Act: 0.1399. Min Act: -0.0000

Data Index: 312707 (C4 (Web Text))

Max Activating Token Index: 817

Text #4

Max Range: 0.1645. Min Range: -0.1645

Max Act: 0.1126. Min Act: -0.0001

Data Index: 291437 (C4 (Web Text))

Max Activating Token Index: 210

Text #5

Max Range: 0.1645. Min Range: -0.1645

Max Act: 0.0974. Min Act: -0.0001

Data Index: 1354974 (C4 (Web Text))

Max Activating Token Index: 625

Text #6

Max Range: 0.1645. Min Range: -0.1645

Max Act: 0.1109. Min Act: -0.0001

Data Index: 38045 (C4 (Web Text))

Max Activating Token Index: 324

Text #7

Max Range: 0.1645. Min Range: -0.1645

Max Act: 0.1076. Min Act: -0.0001

Data Index: 1098083 (C4 (Web Text))

Max Activating Token Index: 299

Text #8

Max Range: 0.1645. Min Range: -0.1645

Max Act: 0.1068. Min Act: -0.0001

Data Index: 1156607 (C4 (Web Text))

Max Activating Token Index: 99

Text #9

Max Range: 0.1645. Min Range: -0.1645

Max Act: 0.0988. Min Act: -0.0001

Data Index: 1214512 (C4 (Web Text))

Max Activating Token Index: 40

Text #10

Max Range: 0.1645. Min Range: -0.1645

Max Act: 0.1016. Min Act: -0.0001

Data Index: 1152192 (C4 (Web Text))

Max Activating Token Index: 45

Text #11

Max Range: 0.1645. Min Range: -0.1645

Max Act: 0.1052. Min Act: -0.0001

Data Index: 557515 (C4 (Web Text))

Max Activating Token Index: 133

Text #12

Max Range: 0.1645. Min Range: -0.1645

Max Act: 0.0940. Min Act: -0.0001

Data Index: 588383 (C4 (Web Text))

Max Activating Token Index: 549

Text #13

Max Range: 0.1645. Min Range: -0.1645

Max Act: 0.0962. Min Act: -0.0001

Data Index: 540133 (C4 (Web Text))

Max Activating Token Index: 218

Text #14

Max Range: 0.1645. Min Range: -0.1645

Max Act: 0.0957. Min Act: -0.0001

Data Index: 897130 (C4 (Web Text))

Max Activating Token Index: 490

Text #15

Max Range: 0.1645. Min Range: -0.1645

Max Act: 0.1004. Min Act: -0.0001

Data Index: 1009702 (C4 (Web Text))

Max Activating Token Index: 836

Text #16

Max Range: 0.1645. Min Range: -0.1645

Max Act: 0.0929. Min Act: -0.0001

Data Index: 1267590 (C4 (Web Text))

Max Activating Token Index: 303

Text #17

Max Range: 0.1645. Min Range: -0.1645

Max Act: 0.0898. Min Act: -0.0001

Data Index: 899960 (C4 (Web Text))

Max Activating Token Index: 675

Text #18

Max Range: 0.1645. Min Range: -0.1645

Max Act: 0.0891. Min Act: -0.0001

Data Index: 347557 (C4 (Web Text))

Max Activating Token Index: 391

Text #19

Max Range: 0.1645. Min Range: -0.1645

Max Act: 0.0921. Min Act: -0.0001

Data Index: 623461 (C4 (Web Text))

Max Activating Token Index: 819