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

Dataset: The Pile

Neuron 4235 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4444. Min Range: -1.4444

Max Act: 1.4444. Min Act: -0.0000

Data Index: 1163009 (The Pile)

Max Activating Token Index: 44

Text #1

Max Range: 1.4444. Min Range: -1.4444

Max Act: 1.3957. Min Act: -0.0000

Data Index: 1911525 (The Pile)

Max Activating Token Index: 98

Text #2

Max Range: 1.4444. Min Range: -1.4444

Max Act: 1.3481. Min Act: -0.0000

Data Index: 330967 (The Pile)

Max Activating Token Index: 94

Text #3

Max Range: 1.4444. Min Range: -1.4444

Max Act: 1.3091. Min Act: -0.0000

Data Index: 734268 (The Pile)

Max Activating Token Index: 244

Text #4

Max Range: 1.4444. Min Range: -1.4444

Max Act: 1.2039. Min Act: -0.0000

Data Index: 297819 (The Pile)

Max Activating Token Index: 90

Text #5

Max Range: 1.4444. Min Range: -1.4444

Max Act: 1.2767. Min Act: -0.0000

Data Index: 1238231 (The Pile)

Max Activating Token Index: 31

Text #6

Max Range: 1.4444. Min Range: -1.4444

Max Act: 1.2465. Min Act: -0.0000

Data Index: 484491 (The Pile)

Max Activating Token Index: 397

Text #7

Max Range: 1.4444. Min Range: -1.4444

Max Act: 1.2384. Min Act: -0.0000

Data Index: 1281354 (The Pile)

Max Activating Token Index: 56

Text #8

Max Range: 1.4444. Min Range: -1.4444

Max Act: 1.1780. Min Act: -0.0000

Data Index: 1208536 (The Pile)

Max Activating Token Index: 285

Text #9

Max Range: 1.4444. Min Range: -1.4444

Max Act: 1.0301. Min Act: -0.0000

Data Index: 468295 (The Pile)

Max Activating Token Index: 979

Text #10

Max Range: 1.4444. Min Range: -1.4444

Max Act: 1.1991. Min Act: -0.0000

Data Index: 1194424 (The Pile)

Max Activating Token Index: 320

Text #11

Max Range: 1.4444. Min Range: -1.4444

Max Act: 1.1898. Min Act: -0.0000

Data Index: 950219 (The Pile)

Max Activating Token Index: 15

Text #12

Max Range: 1.4444. Min Range: -1.4444

Max Act: 1.1091. Min Act: -0.0000

Data Index: 321241 (The Pile)

Max Activating Token Index: 231

Text #13

Max Range: 1.4444. Min Range: -1.4444

Max Act: 1.1328. Min Act: -0.0000

Data Index: 1854914 (The Pile)

Max Activating Token Index: 922

Text #14

Max Range: 1.4444. Min Range: -1.4444

Max Act: 1.1783. Min Act: -0.0000

Data Index: 1840332 (The Pile)

Max Activating Token Index: 375

Text #15

Max Range: 1.4444. Min Range: -1.4444

Max Act: 1.1058. Min Act: -0.0000

Data Index: 204114 (The Pile)

Max Activating Token Index: 404

Text #16

Max Range: 1.4444. Min Range: -1.4444

Max Act: 1.0147. Min Act: -0.0000

Data Index: 1408821 (The Pile)

Max Activating Token Index: 5

Text #17

Max Range: 1.4444. Min Range: -1.4444

Max Act: 1.1090. Min Act: -0.0000

Data Index: 1633607 (The Pile)

Max Activating Token Index: 303

Text #18

Max Range: 1.4444. Min Range: -1.4444

Max Act: 1.0442. Min Act: -0.0000

Data Index: 1229510 (The Pile)

Max Activating Token Index: 757

Text #19

Max Range: 1.4444. Min Range: -1.4444

Max Act: 1.0945. Min Act: -0.0000

Data Index: 314668 (The Pile)

Max Activating Token Index: 15