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

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

Neuron 2201 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8797. Min Range: -0.8797

Max Act: 0.8797. Min Act: -0.0000

Data Index: 878210 (C4 (Web Text))

Max Activating Token Index: 284

Text #1

Max Range: 0.8797. Min Range: -0.8797

Max Act: 0.7699. Min Act: -0.0000

Data Index: 1651687 (Python Code)

Max Activating Token Index: 974

Text #2

Max Range: 0.8797. Min Range: -0.8797

Max Act: 0.7818. Min Act: -0.0000

Data Index: 1377388 (Python Code)

Max Activating Token Index: 570

Text #3

Max Range: 0.8797. Min Range: -0.8797

Max Act: 0.7555. Min Act: -0.0001

Data Index: 1553797 (Python Code)

Max Activating Token Index: 73

Text #4

Max Range: 0.8797. Min Range: -0.8797

Max Act: 0.7507. Min Act: -0.0001

Data Index: 80056 (C4 (Web Text))

Max Activating Token Index: 563

Text #5

Max Range: 0.8797. Min Range: -0.8797

Max Act: 0.6973. Min Act: -0.0001

Data Index: 971436 (C4 (Web Text))

Max Activating Token Index: 633

Text #6

Max Range: 0.8797. Min Range: -0.8797

Max Act: 0.7159. Min Act: -0.0001

Data Index: 649756 (C4 (Web Text))

Max Activating Token Index: 343

Text #7

Max Range: 0.8797. Min Range: -0.8797

Max Act: 0.7092. Min Act: -0.0001

Data Index: 1412525 (Python Code)

Max Activating Token Index: 175

Text #8

Max Range: 0.8797. Min Range: -0.8797

Max Act: 0.7574. Min Act: -0.0000

Data Index: 1191157 (C4 (Web Text))

Max Activating Token Index: 664

Text #9

Max Range: 0.8797. Min Range: -0.8797

Max Act: 0.7554. Min Act: -0.0001

Data Index: 1545952 (Python Code)

Max Activating Token Index: 743

Text #10

Max Range: 0.8797. Min Range: -0.8797

Max Act: 0.7358. Min Act: -0.0000

Data Index: 1499541 (Python Code)

Max Activating Token Index: 237

Text #11

Max Range: 0.8797. Min Range: -0.8797

Max Act: 0.6923. Min Act: -0.0000

Data Index: 920223 (C4 (Web Text))

Max Activating Token Index: 443

Text #12

Max Range: 0.8797. Min Range: -0.8797

Max Act: 0.6729. Min Act: -0.0000

Data Index: 1472808 (Python Code)

Max Activating Token Index: 68

Text #13

Max Range: 0.8797. Min Range: -0.8797

Max Act: 0.6430. Min Act: -0.0000

Data Index: 1408767 (Python Code)

Max Activating Token Index: 79

Text #14

Max Range: 0.8797. Min Range: -0.8797

Max Act: 0.6780. Min Act: -0.0001

Data Index: 636999 (C4 (Web Text))

Max Activating Token Index: 340

Text #15

Max Range: 0.8797. Min Range: -0.8797

Max Act: 0.6566. Min Act: -0.0001

Data Index: 639052 (C4 (Web Text))

Max Activating Token Index: 516

Text #16

Max Range: 0.8797. Min Range: -0.8797

Max Act: 0.6728. Min Act: -0.0000

Data Index: 1366724 (Python Code)

Max Activating Token Index: 434

Text #17

Max Range: 0.8797. Min Range: -0.8797

Max Act: 0.6462. Min Act: -0.0001

Data Index: 1100415 (C4 (Web Text))

Max Activating Token Index: 772

Text #18

Max Range: 0.8797. Min Range: -0.8797

Max Act: 0.6238. Min Act: -0.0001

Data Index: 875738 (C4 (Web Text))

Max Activating Token Index: 808

Text #19

Max Range: 0.8797. Min Range: -0.8797

Max Act: 0.6611. Min Act: -0.0001

Data Index: 709793 (C4 (Web Text))

Max Activating Token Index: 669