Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3074 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.1410. Min Range: -2.1410

Max Act: 2.0041. Min Act: -0.0000

Data Index: 423523 (C4 (Web Text))

Max Activating Token Index: 673

Text #1

Max Range: 2.1410. Min Range: -2.1410

Max Act: 2.1118. Min Act: -0.0000

Data Index: 287228 (C4 (Web Text))

Max Activating Token Index: 220

Text #2

Max Range: 2.1410. Min Range: -2.1410

Max Act: 1.8732. Min Act: -0.0000

Data Index: 17816 (C4 (Web Text))

Max Activating Token Index: 865

Text #3

Max Range: 2.1410. Min Range: -2.1410

Max Act: 1.9735. Min Act: -0.0000

Data Index: 345984 (C4 (Web Text))

Max Activating Token Index: 917

Text #4

Max Range: 2.1410. Min Range: -2.1410

Max Act: 1.9432. Min Act: -0.0000

Data Index: 182274 (C4 (Web Text))

Max Activating Token Index: 541

Text #5

Max Range: 2.1410. Min Range: -2.1410

Max Act: 2.0434. Min Act: -0.0000

Data Index: 692265 (C4 (Web Text))

Max Activating Token Index: 19

Text #6

Max Range: 2.1410. Min Range: -2.1410

Max Act: 2.1410. Min Act: -0.0000

Data Index: 514137 (C4 (Web Text))

Max Activating Token Index: 417

Text #7

Max Range: 2.1410. Min Range: -2.1410

Max Act: 1.9036. Min Act: -0.0000

Data Index: 78560 (C4 (Web Text))

Max Activating Token Index: 937

Text #8

Max Range: 2.1410. Min Range: -2.1410

Max Act: 1.8798. Min Act: -0.0000

Data Index: 658840 (C4 (Web Text))

Max Activating Token Index: 969

Text #9

Max Range: 2.1410. Min Range: -2.1410

Max Act: 1.8401. Min Act: -0.0000

Data Index: 1146765 (C4 (Web Text))

Max Activating Token Index: 984

Text #10

Max Range: 2.1410. Min Range: -2.1410

Max Act: 1.7392. Min Act: -0.0000

Data Index: 1135669 (C4 (Web Text))

Max Activating Token Index: 784

Text #11

Max Range: 2.1410. Min Range: -2.1410

Max Act: 1.9297. Min Act: -0.0000

Data Index: 1266959 (C4 (Web Text))

Max Activating Token Index: 558

Text #12

Max Range: 2.1410. Min Range: -2.1410

Max Act: 2.0294. Min Act: -0.0000

Data Index: 659440 (C4 (Web Text))

Max Activating Token Index: 540

Text #13

Max Range: 2.1410. Min Range: -2.1410

Max Act: 1.9156. Min Act: -0.0000

Data Index: 621525 (C4 (Web Text))

Max Activating Token Index: 67

Text #14

Max Range: 2.1410. Min Range: -2.1410

Max Act: 2.0096. Min Act: -0.0000

Data Index: 1286020 (C4 (Web Text))

Max Activating Token Index: 353

Text #15

Max Range: 2.1410. Min Range: -2.1410

Max Act: 2.0076. Min Act: -0.0000

Data Index: 1217611 (C4 (Web Text))

Max Activating Token Index: 961

Text #16

Max Range: 2.1410. Min Range: -2.1410

Max Act: 1.6653. Min Act: -0.0000

Data Index: 697374 (C4 (Web Text))

Max Activating Token Index: 866

Text #17

Max Range: 2.1410. Min Range: -2.1410

Max Act: 1.7577. Min Act: -0.0000

Data Index: 212909 (C4 (Web Text))

Max Activating Token Index: 152

Text #18

Max Range: 2.1410. Min Range: -2.1410

Max Act: 1.8439. Min Act: -0.0000

Data Index: 46370 (C4 (Web Text))

Max Activating Token Index: 350

Text #19

Max Range: 2.1410. Min Range: -2.1410

Max Act: 1.8514. Min Act: -0.0000

Data Index: 13569 (C4 (Web Text))

Max Activating Token Index: 564