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

Dataset: The Pile

Neuron 1379 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: 0.7674. Min Range: -0.7674

Max Act: 0.7674. Min Act: -0.0000

Data Index: 1280070 (The Pile)

Max Activating Token Index: 82

Text #1

Max Range: 0.7674. Min Range: -0.7674

Max Act: 0.6946. Min Act: -0.0000

Data Index: 1474514 (The Pile)

Max Activating Token Index: 281

Text #2

Max Range: 0.7674. Min Range: -0.7674

Max Act: 0.6766. Min Act: -0.0000

Data Index: 1339030 (The Pile)

Max Activating Token Index: 192

Text #3

Max Range: 0.7674. Min Range: -0.7674

Max Act: 0.7349. Min Act: -0.0000

Data Index: 72994 (The Pile)

Max Activating Token Index: 183

Text #4

Max Range: 0.7674. Min Range: -0.7674

Max Act: 0.6356. Min Act: -0.0000

Data Index: 55793 (The Pile)

Max Activating Token Index: 118

Text #5

Max Range: 0.7674. Min Range: -0.7674

Max Act: 0.6187. Min Act: -0.0000

Data Index: 34262 (The Pile)

Max Activating Token Index: 198

Text #6

Max Range: 0.7674. Min Range: -0.7674

Max Act: 0.6266. Min Act: -0.0000

Data Index: 266695 (The Pile)

Max Activating Token Index: 135

Text #7

Max Range: 0.7674. Min Range: -0.7674

Max Act: 0.6565. Min Act: -0.0000

Data Index: 195528 (The Pile)

Max Activating Token Index: 758

Text #8

Max Range: 0.7674. Min Range: -0.7674

Max Act: 0.6529. Min Act: -0.0000

Data Index: 1428521 (The Pile)

Max Activating Token Index: 163

Text #9

Max Range: 0.7674. Min Range: -0.7674

Max Act: 0.6104. Min Act: -0.0000

Data Index: 45048 (The Pile)

Max Activating Token Index: 144

Text #10

Max Range: 0.7674. Min Range: -0.7674

Max Act: 0.6337. Min Act: -0.0000

Data Index: 1592802 (The Pile)

Max Activating Token Index: 219

Text #11

Max Range: 0.7674. Min Range: -0.7674

Max Act: 0.5822. Min Act: -0.0000

Data Index: 736202 (The Pile)

Max Activating Token Index: 397

Text #12

Max Range: 0.7674. Min Range: -0.7674

Max Act: 0.6100. Min Act: -0.0000

Data Index: 1862666 (The Pile)

Max Activating Token Index: 191

Text #13

Max Range: 0.7674. Min Range: -0.7674

Max Act: 0.5552. Min Act: -0.0000

Data Index: 760443 (The Pile)

Max Activating Token Index: 734

Text #14

Max Range: 0.7674. Min Range: -0.7674

Max Act: 0.5656. Min Act: -0.0000

Data Index: 1129438 (The Pile)

Max Activating Token Index: 63

Text #15

Max Range: 0.7674. Min Range: -0.7674

Max Act: 0.5722. Min Act: -0.0000

Data Index: 1419228 (The Pile)

Max Activating Token Index: 958

Text #16

Max Range: 0.7674. Min Range: -0.7674

Max Act: 0.5460. Min Act: -0.0000

Data Index: 520977 (The Pile)

Max Activating Token Index: 96

Text #17

Max Range: 0.7674. Min Range: -0.7674

Max Act: 0.5980. Min Act: -0.0000

Data Index: 1344589 (The Pile)

Max Activating Token Index: 379

Text #18

Max Range: 0.7674. Min Range: -0.7674

Max Act: 0.5686. Min Act: -0.0000

Data Index: 906634 (The Pile)

Max Activating Token Index: 493

Text #19

Max Range: 0.7674. Min Range: -0.7674

Max Act: 0.5288. Min Act: -0.0000

Data Index: 1293799 (The Pile)

Max Activating Token Index: 885