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

Dataset: The Pile

Neuron 1892 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3016. Min Range: -1.3016

Max Act: 1.3016. Min Act: 0.0000

Data Index: 688157 (The Pile)

Max Activating Token Index: 818

Text #1

Max Range: 1.3016. Min Range: -1.3016

Max Act: 1.0339. Min Act: -0.0000

Data Index: 28149 (The Pile)

Max Activating Token Index: 808

Text #2

Max Range: 1.3016. Min Range: -1.3016

Max Act: 1.1096. Min Act: -0.0000

Data Index: 143654 (The Pile)

Max Activating Token Index: 778

Text #3

Max Range: 1.3016. Min Range: -1.3016

Max Act: 1.1097. Min Act: 0.0001

Data Index: 1921152 (The Pile)

Max Activating Token Index: 473

Text #4

Max Range: 1.3016. Min Range: -1.3016

Max Act: 1.0045. Min Act: -0.0000

Data Index: 117868 (The Pile)

Max Activating Token Index: 1016

Text #5

Max Range: 1.3016. Min Range: -1.3016

Max Act: 1.0501. Min Act: -0.0000

Data Index: 1245909 (The Pile)

Max Activating Token Index: 493

Text #6

Max Range: 1.3016. Min Range: -1.3016

Max Act: 0.9556. Min Act: -0.0000

Data Index: 1946179 (The Pile)

Max Activating Token Index: 225

Text #7

Max Range: 1.3016. Min Range: -1.3016

Max Act: 0.8794. Min Act: 0.0000

Data Index: 1199953 (The Pile)

Max Activating Token Index: 225

Text #8

Max Range: 1.3016. Min Range: -1.3016

Max Act: 0.9698. Min Act: -0.0000

Data Index: 68395 (The Pile)

Max Activating Token Index: 648

Text #9

Max Range: 1.3016. Min Range: -1.3016

Max Act: 0.7869. Min Act: -0.0000

Data Index: 1212000 (The Pile)

Max Activating Token Index: 671

Text #10

Max Range: 1.3016. Min Range: -1.3016

Max Act: 0.8751. Min Act: -0.0000

Data Index: 369663 (The Pile)

Max Activating Token Index: 852

Text #11

Max Range: 1.3016. Min Range: -1.3016

Max Act: 0.9277. Min Act: -0.0000

Data Index: 1951499 (The Pile)

Max Activating Token Index: 900

Text #12

Max Range: 1.3016. Min Range: -1.3016

Max Act: 0.8228. Min Act: -0.0000

Data Index: 1191797 (The Pile)

Max Activating Token Index: 254

Text #13

Max Range: 1.3016. Min Range: -1.3016

Max Act: 0.8388. Min Act: -0.0000

Data Index: 1226196 (The Pile)

Max Activating Token Index: 803

Text #14

Max Range: 1.3016. Min Range: -1.3016

Max Act: 0.8418. Min Act: -0.0000

Data Index: 980636 (The Pile)

Max Activating Token Index: 596

Text #15

Max Range: 1.3016. Min Range: -1.3016

Max Act: 0.8304. Min Act: -0.0000

Data Index: 765366 (The Pile)

Max Activating Token Index: 287

Text #16

Max Range: 1.3016. Min Range: -1.3016

Max Act: 0.8610. Min Act: 0.0000

Data Index: 1172011 (The Pile)

Max Activating Token Index: 183

Text #17

Max Range: 1.3016. Min Range: -1.3016

Max Act: 0.8522. Min Act: 0.0000

Data Index: 768950 (The Pile)

Max Activating Token Index: 355

Text #18

Max Range: 1.3016. Min Range: -1.3016

Max Act: 0.8217. Min Act: -0.0000

Data Index: 605382 (The Pile)

Max Activating Token Index: 67

Text #19

Max Range: 1.3016. Min Range: -1.3016

Max Act: 0.8190. Min Act: 0.0000

Data Index: 922419 (The Pile)

Max Activating Token Index: 30