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

Dataset: The Pile

Neuron 4004 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: 1.2287. Min Range: -1.2287

Max Act: 1.1770. Min Act: -0.0000

Data Index: 613838 (The Pile)

Max Activating Token Index: 1023

Text #1

Max Range: 1.2287. Min Range: -1.2287

Max Act: 1.2287. Min Act: -0.0000

Data Index: 1741793 (The Pile)

Max Activating Token Index: 18

Text #2

Max Range: 1.2287. Min Range: -1.2287

Max Act: 1.0654. Min Act: -0.0000

Data Index: 1512200 (The Pile)

Max Activating Token Index: 382

Text #3

Max Range: 1.2287. Min Range: -1.2287

Max Act: 0.9164. Min Act: -0.0000

Data Index: 714899 (The Pile)

Max Activating Token Index: 365

Text #4

Max Range: 1.2287. Min Range: -1.2287

Max Act: 0.9892. Min Act: -0.0000

Data Index: 334277 (The Pile)

Max Activating Token Index: 383

Text #5

Max Range: 1.2287. Min Range: -1.2287

Max Act: 0.9960. Min Act: -0.0000

Data Index: 1293529 (The Pile)

Max Activating Token Index: 147

Text #6

Max Range: 1.2287. Min Range: -1.2287

Max Act: 0.8580. Min Act: -0.0000

Data Index: 555404 (The Pile)

Max Activating Token Index: 739

Text #7

Max Range: 1.2287. Min Range: -1.2287

Max Act: 0.9742. Min Act: -0.0000

Data Index: 1059566 (The Pile)

Max Activating Token Index: 159

Text #8

Max Range: 1.2287. Min Range: -1.2287

Max Act: 0.8914. Min Act: -0.0000

Data Index: 630536 (The Pile)

Max Activating Token Index: 107

Text #9

Max Range: 1.2287. Min Range: -1.2287

Max Act: 0.8604. Min Act: -0.0000

Data Index: 848916 (The Pile)

Max Activating Token Index: 519

Text #10

Max Range: 1.2287. Min Range: -1.2287

Max Act: 0.8982. Min Act: -0.0000

Data Index: 1022362 (The Pile)

Max Activating Token Index: 247

Text #11

Max Range: 1.2287. Min Range: -1.2287

Max Act: 0.8987. Min Act: -0.0000

Data Index: 1273767 (The Pile)

Max Activating Token Index: 956

Text #12

Max Range: 1.2287. Min Range: -1.2287

Max Act: 0.8138. Min Act: -0.0000

Data Index: 1714169 (The Pile)

Max Activating Token Index: 158

Text #13

Max Range: 1.2287. Min Range: -1.2287

Max Act: 0.9141. Min Act: -0.0000

Data Index: 1426296 (The Pile)

Max Activating Token Index: 209

Text #14

Max Range: 1.2287. Min Range: -1.2287

Max Act: 0.8875. Min Act: -0.0000

Data Index: 724474 (The Pile)

Max Activating Token Index: 203

Text #15

Max Range: 1.2287. Min Range: -1.2287

Max Act: 0.7354. Min Act: -0.0000

Data Index: 1736003 (The Pile)

Max Activating Token Index: 644

Text #16

Max Range: 1.2287. Min Range: -1.2287

Max Act: 0.8964. Min Act: -0.0000

Data Index: 1255568 (The Pile)

Max Activating Token Index: 566

Text #17

Max Range: 1.2287. Min Range: -1.2287

Max Act: 0.8199. Min Act: -0.0000

Data Index: 545862 (The Pile)

Max Activating Token Index: 50

Text #18

Max Range: 1.2287. Min Range: -1.2287

Max Act: 0.8505. Min Act: -0.0000

Data Index: 465509 (The Pile)

Max Activating Token Index: 576

Text #19

Max Range: 1.2287. Min Range: -1.2287

Max Act: 0.8569. Min Act: -0.0000

Data Index: 853084 (The Pile)

Max Activating Token Index: 434