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

Dataset: The Pile

Neuron 1955 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: 0.5591. Min Range: -0.5591

Max Act: 0.5489. Min Act: -0.0000

Data Index: 1884167 (The Pile)

Max Activating Token Index: 346

Text #1

Max Range: 0.5591. Min Range: -0.5591

Max Act: 0.5591. Min Act: -0.0000

Data Index: 1243335 (The Pile)

Max Activating Token Index: 782

Text #2

Max Range: 0.5591. Min Range: -0.5591

Max Act: 0.4866. Min Act: -0.0000

Data Index: 80639 (The Pile)

Max Activating Token Index: 728

Text #3

Max Range: 0.5591. Min Range: -0.5591

Max Act: 0.4969. Min Act: -0.0000

Data Index: 812404 (The Pile)

Max Activating Token Index: 53

Text #4

Max Range: 0.5591. Min Range: -0.5591

Max Act: 0.4934. Min Act: -0.0000

Data Index: 1956596 (The Pile)

Max Activating Token Index: 937

Text #5

Max Range: 0.5591. Min Range: -0.5591

Max Act: 0.4748. Min Act: -0.0000

Data Index: 991535 (The Pile)

Max Activating Token Index: 179

Text #6

Max Range: 0.5591. Min Range: -0.5591

Max Act: 0.4531. Min Act: -0.0000

Data Index: 834329 (The Pile)

Max Activating Token Index: 623

Text #7

Max Range: 0.5591. Min Range: -0.5591

Max Act: 0.5304. Min Act: -0.0000

Data Index: 1233734 (The Pile)

Max Activating Token Index: 701

Text #8

Max Range: 0.5591. Min Range: -0.5591

Max Act: 0.4432. Min Act: -0.0000

Data Index: 347577 (The Pile)

Max Activating Token Index: 656

Text #9

Max Range: 0.5591. Min Range: -0.5591

Max Act: 0.4655. Min Act: -0.0000

Data Index: 1445297 (The Pile)

Max Activating Token Index: 381

Text #10

Max Range: 0.5591. Min Range: -0.5591

Max Act: 0.4289. Min Act: -0.0000

Data Index: 227101 (The Pile)

Max Activating Token Index: 33

Text #11

Max Range: 0.5591. Min Range: -0.5591

Max Act: 0.4176. Min Act: -0.0000

Data Index: 1414130 (The Pile)

Max Activating Token Index: 764

Text #12

Max Range: 0.5591. Min Range: -0.5591

Max Act: 0.4194. Min Act: -0.0000

Data Index: 1248679 (The Pile)

Max Activating Token Index: 316

Text #13

Max Range: 0.5591. Min Range: -0.5591

Max Act: 0.4061. Min Act: -0.0000

Data Index: 1447074 (The Pile)

Max Activating Token Index: 205

Text #14

Max Range: 0.5591. Min Range: -0.5591

Max Act: 0.3492. Min Act: -0.0000

Data Index: 1677793 (The Pile)

Max Activating Token Index: 886

Text #15

Max Range: 0.5591. Min Range: -0.5591

Max Act: 0.4369. Min Act: -0.0000

Data Index: 75256 (The Pile)

Max Activating Token Index: 784

Text #16

Max Range: 0.5591. Min Range: -0.5591

Max Act: 0.4109. Min Act: -0.0000

Data Index: 620875 (The Pile)

Max Activating Token Index: 866

Text #17

Max Range: 0.5591. Min Range: -0.5591

Max Act: 0.4015. Min Act: -0.0000

Data Index: 1817633 (The Pile)

Max Activating Token Index: 420

Text #18

Max Range: 0.5591. Min Range: -0.5591

Max Act: 0.4312. Min Act: -0.0000

Data Index: 1762340 (The Pile)

Max Activating Token Index: 862

Text #19

Max Range: 0.5591. Min Range: -0.5591

Max Act: 0.3901. Min Act: -0.0000

Data Index: 452358 (The Pile)

Max Activating Token Index: 354