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

Dataset: The Pile

Neuron 4895 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1102. Min Range: -1.1102

Max Act: 0.7700. Min Act: -0.0000

Data Index: 1220320 (The Pile)

Max Activating Token Index: 179

Text #1

Max Range: 1.1102. Min Range: -1.1102

Max Act: 1.1102. Min Act: -0.0000

Data Index: 877399 (The Pile)

Max Activating Token Index: 106

Text #2

Max Range: 1.1102. Min Range: -1.1102

Max Act: 0.7186. Min Act: -0.0000

Data Index: 995832 (The Pile)

Max Activating Token Index: 344

Text #3

Max Range: 1.1102. Min Range: -1.1102

Max Act: 0.7990. Min Act: -0.0000

Data Index: 1478930 (The Pile)

Max Activating Token Index: 527

Text #4

Max Range: 1.1102. Min Range: -1.1102

Max Act: 0.6453. Min Act: -0.0000

Data Index: 1698495 (The Pile)

Max Activating Token Index: 1001

Text #5

Max Range: 1.1102. Min Range: -1.1102

Max Act: 0.6747. Min Act: -0.0000

Data Index: 336530 (The Pile)

Max Activating Token Index: 86

Text #6

Max Range: 1.1102. Min Range: -1.1102

Max Act: 0.6612. Min Act: -0.0000

Data Index: 1424283 (The Pile)

Max Activating Token Index: 622

Text #7

Max Range: 1.1102. Min Range: -1.1102

Max Act: 0.8419. Min Act: -0.0000

Data Index: 974986 (The Pile)

Max Activating Token Index: 485

Text #8

Max Range: 1.1102. Min Range: -1.1102

Max Act: 0.4688. Min Act: -0.0000

Data Index: 1918092 (The Pile)

Max Activating Token Index: 178

Text #9

Max Range: 1.1102. Min Range: -1.1102

Max Act: 0.5053. Min Act: -0.0000

Data Index: 1508177 (The Pile)

Max Activating Token Index: 719

Text #10

Max Range: 1.1102. Min Range: -1.1102

Max Act: 0.6015. Min Act: -0.0000

Data Index: 297760 (The Pile)

Max Activating Token Index: 319

Text #11

Max Range: 1.1102. Min Range: -1.1102

Max Act: 0.5395. Min Act: -0.0000

Data Index: 1855242 (The Pile)

Max Activating Token Index: 614

Text #12

Max Range: 1.1102. Min Range: -1.1102

Max Act: 0.6082. Min Act: -0.0000

Data Index: 344855 (The Pile)

Max Activating Token Index: 712

Text #13

Max Range: 1.1102. Min Range: -1.1102

Max Act: 0.4314. Min Act: -0.0000

Data Index: 1589594 (The Pile)

Max Activating Token Index: 881

Text #14

Max Range: 1.1102. Min Range: -1.1102

Max Act: 0.5291. Min Act: -0.0000

Data Index: 44641 (The Pile)

Max Activating Token Index: 258

Text #15

Max Range: 1.1102. Min Range: -1.1102

Max Act: 0.6150. Min Act: -0.0000

Data Index: 1701131 (The Pile)

Max Activating Token Index: 687

Text #16

Max Range: 1.1102. Min Range: -1.1102

Max Act: 0.5151. Min Act: -0.0000

Data Index: 249084 (The Pile)

Max Activating Token Index: 285

Text #17

Max Range: 1.1102. Min Range: -1.1102

Max Act: 0.4743. Min Act: -0.0000

Data Index: 1912001 (The Pile)

Max Activating Token Index: 242

Text #18

Max Range: 1.1102. Min Range: -1.1102

Max Act: 0.5700. Min Act: -0.0000

Data Index: 1544890 (The Pile)

Max Activating Token Index: 739

Text #19

Max Range: 1.1102. Min Range: -1.1102

Max Act: 0.4955. Min Act: -0.0000

Data Index: 1759306 (The Pile)

Max Activating Token Index: 260