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

Dataset: The Pile

Neuron 888 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 3.0339. Min Range: -3.0339

Max Act: 3.0228. Min Act: -0.0000

Data Index: 711274 (The Pile)

Max Activating Token Index: 963

Text #1

Max Range: 3.0339. Min Range: -3.0339

Max Act: 3.0339. Min Act: -0.0000

Data Index: 736207 (The Pile)

Max Activating Token Index: 865

Text #2

Max Range: 3.0339. Min Range: -3.0339

Max Act: 2.9309. Min Act: -0.0000

Data Index: 1416677 (The Pile)

Max Activating Token Index: 674

Text #3

Max Range: 3.0339. Min Range: -3.0339

Max Act: 2.9256. Min Act: -0.0000

Data Index: 1263487 (The Pile)

Max Activating Token Index: 434

Text #4

Max Range: 3.0339. Min Range: -3.0339

Max Act: 2.5800. Min Act: -0.0000

Data Index: 248422 (The Pile)

Max Activating Token Index: 238

Text #5

Max Range: 3.0339. Min Range: -3.0339

Max Act: 2.1204. Min Act: -0.0000

Data Index: 1045887 (The Pile)

Max Activating Token Index: 607

Text #6

Max Range: 3.0339. Min Range: -3.0339

Max Act: 1.8107. Min Act: -0.0000

Data Index: 704885 (The Pile)

Max Activating Token Index: 406

Text #7

Max Range: 3.0339. Min Range: -3.0339

Max Act: 1.8767. Min Act: -0.0000

Data Index: 1869649 (The Pile)

Max Activating Token Index: 707

Text #8

Max Range: 3.0339. Min Range: -3.0339

Max Act: 1.8132. Min Act: -0.0000

Data Index: 761042 (The Pile)

Max Activating Token Index: 136

Text #9

Max Range: 3.0339. Min Range: -3.0339

Max Act: 1.7349. Min Act: -0.0000

Data Index: 1637924 (The Pile)

Max Activating Token Index: 392

Text #10

Max Range: 3.0339. Min Range: -3.0339

Max Act: 1.5830. Min Act: -0.0000

Data Index: 898266 (The Pile)

Max Activating Token Index: 520

Text #11

Max Range: 3.0339. Min Range: -3.0339

Max Act: 1.5107. Min Act: -0.0000

Data Index: 1735640 (The Pile)

Max Activating Token Index: 589

Text #12

Max Range: 3.0339. Min Range: -3.0339

Max Act: 1.4089. Min Act: -0.0000

Data Index: 1411025 (The Pile)

Max Activating Token Index: 363

Text #13

Max Range: 3.0339. Min Range: -3.0339

Max Act: 1.3008. Min Act: -0.0000

Data Index: 625735 (The Pile)

Max Activating Token Index: 799

Text #14

Max Range: 3.0339. Min Range: -3.0339

Max Act: 1.2987. Min Act: -0.0000

Data Index: 994706 (The Pile)

Max Activating Token Index: 90

Text #15

Max Range: 3.0339. Min Range: -3.0339

Max Act: 1.2962. Min Act: -0.0000

Data Index: 1685540 (The Pile)

Max Activating Token Index: 959

Text #16

Max Range: 3.0339. Min Range: -3.0339

Max Act: 1.3548. Min Act: 0.0000

Data Index: 1583364 (The Pile)

Max Activating Token Index: 156

Text #17

Max Range: 3.0339. Min Range: -3.0339

Max Act: 1.3062. Min Act: -0.0000

Data Index: 1324679 (The Pile)

Max Activating Token Index: 117

Text #18

Max Range: 3.0339. Min Range: -3.0339

Max Act: 1.2761. Min Act: -0.0000

Data Index: 384999 (The Pile)

Max Activating Token Index: 759

Text #19

Max Range: 3.0339. Min Range: -3.0339

Max Act: 1.2857. Min Act: -0.0000

Data Index: 468620 (The Pile)

Max Activating Token Index: 707