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

Dataset: The Pile

Neuron 3499 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.4506. Min Act: -0.0000

Data Index: 1107184 (The Pile)

Max Activating Token Index: 611

Text #1

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.5405. Min Act: -0.0000

Data Index: 114592 (The Pile)

Max Activating Token Index: 820

Text #2

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.5581. Min Act: -0.0000

Data Index: 161325 (The Pile)

Max Activating Token Index: 413

Text #3

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.5590. Min Act: -0.0000

Data Index: 325856 (The Pile)

Max Activating Token Index: 645

Text #4

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.5554. Min Act: -0.0000

Data Index: 336363 (The Pile)

Max Activating Token Index: 233

Text #5

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.5285. Min Act: -0.0000

Data Index: 84860 (The Pile)

Max Activating Token Index: 365

Text #6

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.4805. Min Act: -0.0000

Data Index: 1785766 (The Pile)

Max Activating Token Index: 198

Text #7

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.5551. Min Act: -0.0000

Data Index: 1364231 (The Pile)

Max Activating Token Index: 161

Text #8

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.5379. Min Act: -0.0000

Data Index: 1918401 (The Pile)

Max Activating Token Index: 160

Text #9

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.5079. Min Act: -0.0000

Data Index: 849206 (The Pile)

Max Activating Token Index: 363

Text #10

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.5226. Min Act: -0.0000

Data Index: 1568197 (The Pile)

Max Activating Token Index: 821

Text #11

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.5020. Min Act: -0.0000

Data Index: 615083 (The Pile)

Max Activating Token Index: 274

Text #12

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.5012. Min Act: -0.0000

Data Index: 203958 (The Pile)

Max Activating Token Index: 770

Text #13

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.4822. Min Act: -0.0000

Data Index: 1496260 (The Pile)

Max Activating Token Index: 334

Text #14

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.5147. Min Act: -0.0000

Data Index: 569063 (The Pile)

Max Activating Token Index: 1014

Text #15

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.5093. Min Act: -0.0000

Data Index: 861275 (The Pile)

Max Activating Token Index: 776

Text #16

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.5184. Min Act: -0.0000

Data Index: 252030 (The Pile)

Max Activating Token Index: 139

Text #17

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.4427. Min Act: -0.0000

Data Index: 1608115 (The Pile)

Max Activating Token Index: 944

Text #18

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.5233. Min Act: -0.0000

Data Index: 1658143 (The Pile)

Max Activating Token Index: 261

Text #19

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.4630. Min Act: -0.0000

Data Index: 1586536 (The Pile)

Max Activating Token Index: 804