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

Dataset: The Pile

Neuron 2896 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9152. Min Range: -0.9152

Max Act: 0.9152. Min Act: -0.0000

Data Index: 1152427 (The Pile)

Max Activating Token Index: 311

Text #1

Max Range: 0.9152. Min Range: -0.9152

Max Act: 0.7922. Min Act: -0.0000

Data Index: 1911323 (The Pile)

Max Activating Token Index: 550

Text #2

Max Range: 0.9152. Min Range: -0.9152

Max Act: 0.7418. Min Act: -0.0000

Data Index: 258130 (The Pile)

Max Activating Token Index: 94

Text #3

Max Range: 0.9152. Min Range: -0.9152

Max Act: 0.7190. Min Act: -0.0000

Data Index: 1293746 (The Pile)

Max Activating Token Index: 666

Text #4

Max Range: 0.9152. Min Range: -0.9152

Max Act: 0.7653. Min Act: -0.0000

Data Index: 582094 (The Pile)

Max Activating Token Index: 162

Text #5

Max Range: 0.9152. Min Range: -0.9152

Max Act: 0.6308. Min Act: -0.0000

Data Index: 663697 (The Pile)

Max Activating Token Index: 612

Text #6

Max Range: 0.9152. Min Range: -0.9152

Max Act: 0.6949. Min Act: -0.0000

Data Index: 1212288 (The Pile)

Max Activating Token Index: 921

Text #7

Max Range: 0.9152. Min Range: -0.9152

Max Act: 0.6685. Min Act: -0.0000

Data Index: 993067 (The Pile)

Max Activating Token Index: 198

Text #8

Max Range: 0.9152. Min Range: -0.9152

Max Act: 0.6869. Min Act: -0.0000

Data Index: 1631960 (The Pile)

Max Activating Token Index: 58

Text #9

Max Range: 0.9152. Min Range: -0.9152

Max Act: 0.6699. Min Act: -0.0000

Data Index: 822849 (The Pile)

Max Activating Token Index: 262

Text #10

Max Range: 0.9152. Min Range: -0.9152

Max Act: 0.6440. Min Act: -0.0000

Data Index: 677229 (The Pile)

Max Activating Token Index: 402

Text #11

Max Range: 0.9152. Min Range: -0.9152

Max Act: 0.6573. Min Act: -0.0000

Data Index: 941892 (The Pile)

Max Activating Token Index: 369

Text #12

Max Range: 0.9152. Min Range: -0.9152

Max Act: 0.6157. Min Act: -0.0000

Data Index: 1206980 (The Pile)

Max Activating Token Index: 514

Text #13

Max Range: 0.9152. Min Range: -0.9152

Max Act: 0.6105. Min Act: -0.0000

Data Index: 1906517 (The Pile)

Max Activating Token Index: 642

Text #14

Max Range: 0.9152. Min Range: -0.9152

Max Act: 0.6113. Min Act: -0.0000

Data Index: 1527586 (The Pile)

Max Activating Token Index: 886

Text #15

Max Range: 0.9152. Min Range: -0.9152

Max Act: 0.5955. Min Act: -0.0000

Data Index: 1467464 (The Pile)

Max Activating Token Index: 565

Text #16

Max Range: 0.9152. Min Range: -0.9152

Max Act: 0.5678. Min Act: -0.0000

Data Index: 1070395 (The Pile)

Max Activating Token Index: 368

Text #17

Max Range: 0.9152. Min Range: -0.9152

Max Act: 0.6406. Min Act: -0.0000

Data Index: 353240 (The Pile)

Max Activating Token Index: 868

Text #18

Max Range: 0.9152. Min Range: -0.9152

Max Act: 0.5788. Min Act: -0.0000

Data Index: 524329 (The Pile)

Max Activating Token Index: 66

Text #19

Max Range: 0.9152. Min Range: -0.9152

Max Act: 0.5616. Min Act: -0.0000

Data Index: 1088193 (The Pile)

Max Activating Token Index: 165