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

Dataset: The Pile

Neuron 972 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: 0.8117. Min Range: -0.8117

Max Act: 0.7972. Min Act: -0.0000

Data Index: 319997 (The Pile)

Max Activating Token Index: 413

Text #1

Max Range: 0.8117. Min Range: -0.8117

Max Act: 0.7062. Min Act: -0.0000

Data Index: 1403997 (The Pile)

Max Activating Token Index: 209

Text #2

Max Range: 0.8117. Min Range: -0.8117

Max Act: 0.7743. Min Act: -0.0000

Data Index: 1654372 (The Pile)

Max Activating Token Index: 301

Text #3

Max Range: 0.8117. Min Range: -0.8117

Max Act: 0.6704. Min Act: -0.0000

Data Index: 235656 (The Pile)

Max Activating Token Index: 189

Text #4

Max Range: 0.8117. Min Range: -0.8117

Max Act: 0.7450. Min Act: -0.0000

Data Index: 538122 (The Pile)

Max Activating Token Index: 318

Text #5

Max Range: 0.8117. Min Range: -0.8117

Max Act: 0.8117. Min Act: -0.0000

Data Index: 593780 (The Pile)

Max Activating Token Index: 196

Text #6

Max Range: 0.8117. Min Range: -0.8117

Max Act: 0.8096. Min Act: -0.0000

Data Index: 237522 (The Pile)

Max Activating Token Index: 233

Text #7

Max Range: 0.8117. Min Range: -0.8117

Max Act: 0.5912. Min Act: -0.0000

Data Index: 300912 (The Pile)

Max Activating Token Index: 181

Text #8

Max Range: 0.8117. Min Range: -0.8117

Max Act: 0.6327. Min Act: -0.0000

Data Index: 1901758 (The Pile)

Max Activating Token Index: 433

Text #9

Max Range: 0.8117. Min Range: -0.8117

Max Act: 0.5631. Min Act: -0.0000

Data Index: 1514107 (The Pile)

Max Activating Token Index: 852

Text #10

Max Range: 0.8117. Min Range: -0.8117

Max Act: 0.5685. Min Act: -0.0000

Data Index: 1124679 (The Pile)

Max Activating Token Index: 163

Text #11

Max Range: 0.8117. Min Range: -0.8117

Max Act: 0.6058. Min Act: -0.0000

Data Index: 1913490 (The Pile)

Max Activating Token Index: 776

Text #12

Max Range: 0.8117. Min Range: -0.8117

Max Act: 0.5555. Min Act: -0.0000

Data Index: 463473 (The Pile)

Max Activating Token Index: 891

Text #13

Max Range: 0.8117. Min Range: -0.8117

Max Act: 0.6871. Min Act: -0.0000

Data Index: 840118 (The Pile)

Max Activating Token Index: 141

Text #14

Max Range: 0.8117. Min Range: -0.8117

Max Act: 0.6483. Min Act: -0.0000

Data Index: 533385 (The Pile)

Max Activating Token Index: 972

Text #15

Max Range: 0.8117. Min Range: -0.8117

Max Act: 0.5502. Min Act: 0.0000

Data Index: 865650 (The Pile)

Max Activating Token Index: 453

Text #16

Max Range: 0.8117. Min Range: -0.8117

Max Act: 0.5813. Min Act: -0.0000

Data Index: 20329 (The Pile)

Max Activating Token Index: 973

Text #17

Max Range: 0.8117. Min Range: -0.8117

Max Act: 0.5806. Min Act: -0.0000

Data Index: 1152310 (The Pile)

Max Activating Token Index: 421

Text #18

Max Range: 0.8117. Min Range: -0.8117

Max Act: 0.5145. Min Act: -0.0000

Data Index: 1730938 (The Pile)

Max Activating Token Index: 558

Text #19

Max Range: 0.8117. Min Range: -0.8117

Max Act: 0.4945. Min Act: -0.0000

Data Index: 519360 (The Pile)

Max Activating Token Index: 488