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

Dataset: The Pile

Neuron 2055 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.7276. Min Range: -0.7276

Max Act: 0.7276. Min Act: -0.0000

Data Index: 1345180 (The Pile)

Max Activating Token Index: 892

Text #1

Max Range: 0.7276. Min Range: -0.7276

Max Act: 0.6125. Min Act: -0.0000

Data Index: 1676553 (The Pile)

Max Activating Token Index: 251

Text #2

Max Range: 0.7276. Min Range: -0.7276

Max Act: 0.5690. Min Act: -0.0000

Data Index: 200017 (The Pile)

Max Activating Token Index: 481

Text #3

Max Range: 0.7276. Min Range: -0.7276

Max Act: 0.4652. Min Act: -0.0000

Data Index: 1709910 (The Pile)

Max Activating Token Index: 620

Text #4

Max Range: 0.7276. Min Range: -0.7276

Max Act: 0.5116. Min Act: -0.0000

Data Index: 1747480 (The Pile)

Max Activating Token Index: 241

Text #5

Max Range: 0.7276. Min Range: -0.7276

Max Act: 0.4460. Min Act: -0.0000

Data Index: 1647297 (The Pile)

Max Activating Token Index: 254

Text #6

Max Range: 0.7276. Min Range: -0.7276

Max Act: 0.4644. Min Act: -0.0000

Data Index: 1968061 (The Pile)

Max Activating Token Index: 428

Text #7

Max Range: 0.7276. Min Range: -0.7276

Max Act: 0.4353. Min Act: -0.0000

Data Index: 1421592 (The Pile)

Max Activating Token Index: 157

Text #8

Max Range: 0.7276. Min Range: -0.7276

Max Act: 0.4422. Min Act: -0.0000

Data Index: 1443764 (The Pile)

Max Activating Token Index: 151

Text #9

Max Range: 0.7276. Min Range: -0.7276

Max Act: 0.4325. Min Act: -0.0000

Data Index: 1223326 (The Pile)

Max Activating Token Index: 868

Text #10

Max Range: 0.7276. Min Range: -0.7276

Max Act: 0.4336. Min Act: -0.0000

Data Index: 1276094 (The Pile)

Max Activating Token Index: 624

Text #11

Max Range: 0.7276. Min Range: -0.7276

Max Act: 0.4307. Min Act: -0.0000

Data Index: 662797 (The Pile)

Max Activating Token Index: 760

Text #12

Max Range: 0.7276. Min Range: -0.7276

Max Act: 0.3947. Min Act: -0.0000

Data Index: 1427835 (The Pile)

Max Activating Token Index: 163

Text #13

Max Range: 0.7276. Min Range: -0.7276

Max Act: 0.4083. Min Act: 0.0000

Data Index: 670962 (The Pile)

Max Activating Token Index: 424

Text #14

Max Range: 0.7276. Min Range: -0.7276

Max Act: 0.4198. Min Act: -0.0000

Data Index: 335978 (The Pile)

Max Activating Token Index: 122

Text #15

Max Range: 0.7276. Min Range: -0.7276

Max Act: 0.4090. Min Act: 0.0000

Data Index: 553446 (The Pile)

Max Activating Token Index: 330

Text #16

Max Range: 0.7276. Min Range: -0.7276

Max Act: 0.4180. Min Act: -0.0000

Data Index: 316686 (The Pile)

Max Activating Token Index: 599

Text #17

Max Range: 0.7276. Min Range: -0.7276

Max Act: 0.4335. Min Act: -0.0000

Data Index: 1817835 (The Pile)

Max Activating Token Index: 924

Text #18

Max Range: 0.7276. Min Range: -0.7276

Max Act: 0.4148. Min Act: -0.0000

Data Index: 63247 (The Pile)

Max Activating Token Index: 546

Text #19

Max Range: 0.7276. Min Range: -0.7276

Max Act: 0.3860. Min Act: -0.0000

Data Index: 205452 (The Pile)

Max Activating Token Index: 109