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

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

Neuron 4917 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: 1.1784. Min Range: -1.1784

Max Act: 1.1562. Min Act: -0.0000

Data Index: 112440 (C4 (Web Text))

Max Activating Token Index: 884

Text #1

Max Range: 1.1784. Min Range: -1.1784

Max Act: 1.1784. Min Act: -0.0000

Data Index: 716795 (C4 (Web Text))

Max Activating Token Index: 944

Text #2

Max Range: 1.1784. Min Range: -1.1784

Max Act: 1.0543. Min Act: -0.0000

Data Index: 50181 (C4 (Web Text))

Max Activating Token Index: 980

Text #3

Max Range: 1.1784. Min Range: -1.1784

Max Act: 0.9992. Min Act: -0.0000

Data Index: 844824 (C4 (Web Text))

Max Activating Token Index: 682

Text #4

Max Range: 1.1784. Min Range: -1.1784

Max Act: 0.9786. Min Act: -0.0000

Data Index: 1318784 (C4 (Web Text))

Max Activating Token Index: 292

Text #5

Max Range: 1.1784. Min Range: -1.1784

Max Act: 0.9763. Min Act: -0.0000

Data Index: 592513 (C4 (Web Text))

Max Activating Token Index: 647

Text #6

Max Range: 1.1784. Min Range: -1.1784

Max Act: 0.9538. Min Act: -0.0000

Data Index: 736868 (C4 (Web Text))

Max Activating Token Index: 475

Text #7

Max Range: 1.1784. Min Range: -1.1784

Max Act: 0.9562. Min Act: -0.0000

Data Index: 1304734 (C4 (Web Text))

Max Activating Token Index: 659

Text #8

Max Range: 1.1784. Min Range: -1.1784

Max Act: 0.8917. Min Act: -0.0000

Data Index: 140870 (C4 (Web Text))

Max Activating Token Index: 628

Text #9

Max Range: 1.1784. Min Range: -1.1784

Max Act: 0.8641. Min Act: -0.0000

Data Index: 491183 (C4 (Web Text))

Max Activating Token Index: 651

Text #10

Max Range: 1.1784. Min Range: -1.1784

Max Act: 0.8830. Min Act: -0.0000

Data Index: 1041056 (C4 (Web Text))

Max Activating Token Index: 364

Text #11

Max Range: 1.1784. Min Range: -1.1784

Max Act: 0.8983. Min Act: -0.0000

Data Index: 9026 (C4 (Web Text))

Max Activating Token Index: 565

Text #12

Max Range: 1.1784. Min Range: -1.1784

Max Act: 0.9547. Min Act: -0.0000

Data Index: 823500 (C4 (Web Text))

Max Activating Token Index: 920

Text #13

Max Range: 1.1784. Min Range: -1.1784

Max Act: 0.9174. Min Act: -0.0000

Data Index: 617256 (C4 (Web Text))

Max Activating Token Index: 757

Text #14

Max Range: 1.1784. Min Range: -1.1784

Max Act: 0.8743. Min Act: -0.0001

Data Index: 230121 (C4 (Web Text))

Max Activating Token Index: 828

Text #15

Max Range: 1.1784. Min Range: -1.1784

Max Act: 0.9219. Min Act: -0.0000

Data Index: 1098191 (C4 (Web Text))

Max Activating Token Index: 171

Text #16

Max Range: 1.1784. Min Range: -1.1784

Max Act: 0.8942. Min Act: -0.0000

Data Index: 919684 (C4 (Web Text))

Max Activating Token Index: 973

Text #17

Max Range: 1.1784. Min Range: -1.1784

Max Act: 0.8307. Min Act: -0.0001

Data Index: 215122 (C4 (Web Text))

Max Activating Token Index: 558

Text #18

Max Range: 1.1784. Min Range: -1.1784

Max Act: 0.8585. Min Act: -0.0000

Data Index: 343677 (C4 (Web Text))

Max Activating Token Index: 162

Text #19

Max Range: 1.1784. Min Range: -1.1784

Max Act: 0.8518. Min Act: -0.0000

Data Index: 292793 (C4 (Web Text))

Max Activating Token Index: 857