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

Dataset: The Pile

Neuron 68 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8430. Min Range: -0.8430

Max Act: 0.8430. Min Act: -0.0000

Data Index: 1071036 (The Pile)

Max Activating Token Index: 207

Text #1

Max Range: 0.8430. Min Range: -0.8430

Max Act: 0.6743. Min Act: -0.0000

Data Index: 1540342 (The Pile)

Max Activating Token Index: 111

Text #2

Max Range: 0.8430. Min Range: -0.8430

Max Act: 0.7384. Min Act: -0.0000

Data Index: 320384 (The Pile)

Max Activating Token Index: 230

Text #3

Max Range: 0.8430. Min Range: -0.8430

Max Act: 0.7492. Min Act: -0.0000

Data Index: 1757957 (The Pile)

Max Activating Token Index: 79

Text #4

Max Range: 0.8430. Min Range: -0.8430

Max Act: 0.7326. Min Act: -0.0000

Data Index: 852495 (The Pile)

Max Activating Token Index: 448

Text #5

Max Range: 0.8430. Min Range: -0.8430

Max Act: 0.6992. Min Act: 0.0000

Data Index: 671577 (The Pile)

Max Activating Token Index: 398

Text #6

Max Range: 0.8430. Min Range: -0.8430

Max Act: 0.7173. Min Act: 0.0001

Data Index: 1956037 (The Pile)

Max Activating Token Index: 220

Text #7

Max Range: 0.8430. Min Range: -0.8430

Max Act: 0.6014. Min Act: -0.0000

Data Index: 1664650 (The Pile)

Max Activating Token Index: 167

Text #8

Max Range: 0.8430. Min Range: -0.8430

Max Act: 0.6673. Min Act: -0.0000

Data Index: 824795 (The Pile)

Max Activating Token Index: 250

Text #9

Max Range: 0.8430. Min Range: -0.8430

Max Act: 0.7677. Min Act: -0.0000

Data Index: 859208 (The Pile)

Max Activating Token Index: 957

Text #10

Max Range: 0.8430. Min Range: -0.8430

Max Act: 0.6540. Min Act: -0.0000

Data Index: 1893346 (The Pile)

Max Activating Token Index: 188

Text #11

Max Range: 0.8430. Min Range: -0.8430

Max Act: 0.5269. Min Act: -0.0000

Data Index: 1769390 (The Pile)

Max Activating Token Index: 173

Text #12

Max Range: 0.8430. Min Range: -0.8430

Max Act: 0.6634. Min Act: -0.0000

Data Index: 1772276 (The Pile)

Max Activating Token Index: 519

Text #13

Max Range: 0.8430. Min Range: -0.8430

Max Act: 0.6368. Min Act: -0.0000

Data Index: 898146 (The Pile)

Max Activating Token Index: 73

Text #14

Max Range: 0.8430. Min Range: -0.8430

Max Act: 0.6072. Min Act: -0.0000

Data Index: 721100 (The Pile)

Max Activating Token Index: 230

Text #15

Max Range: 0.8430. Min Range: -0.8430

Max Act: 0.6053. Min Act: -0.0000

Data Index: 1767962 (The Pile)

Max Activating Token Index: 269

Text #16

Max Range: 0.8430. Min Range: -0.8430

Max Act: 0.6203. Min Act: 0.0001

Data Index: 431075 (The Pile)

Max Activating Token Index: 681

Text #17

Max Range: 0.8430. Min Range: -0.8430

Max Act: 0.5667. Min Act: -0.0000

Data Index: 1056244 (The Pile)

Max Activating Token Index: 753

Text #18

Max Range: 0.8430. Min Range: -0.8430

Max Act: 0.5941. Min Act: 0.0000

Data Index: 1024940 (The Pile)

Max Activating Token Index: 985

Text #19

Max Range: 0.8430. Min Range: -0.8430

Max Act: 0.5844. Min Act: -0.0000

Data Index: 795779 (The Pile)

Max Activating Token Index: 956