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

Dataset: The Pile

Neuron 2145 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: 0.5218. Min Range: -0.5218

Max Act: 0.5218. Min Act: -0.0000

Data Index: 1508670 (The Pile)

Max Activating Token Index: 825

Text #1

Max Range: 0.5218. Min Range: -0.5218

Max Act: 0.4339. Min Act: -0.0001

Data Index: 1104985 (The Pile)

Max Activating Token Index: 899

Text #2

Max Range: 0.5218. Min Range: -0.5218

Max Act: 0.4808. Min Act: -0.0000

Data Index: 1534087 (The Pile)

Max Activating Token Index: 1003

Text #3

Max Range: 0.5218. Min Range: -0.5218

Max Act: 0.4705. Min Act: -0.0000

Data Index: 1927781 (The Pile)

Max Activating Token Index: 172

Text #4

Max Range: 0.5218. Min Range: -0.5218

Max Act: 0.4795. Min Act: -0.0000

Data Index: 1132284 (The Pile)

Max Activating Token Index: 960

Text #5

Max Range: 0.5218. Min Range: -0.5218

Max Act: 0.4639. Min Act: -0.0000

Data Index: 1641919 (The Pile)

Max Activating Token Index: 40

Text #6

Max Range: 0.5218. Min Range: -0.5218

Max Act: 0.4219. Min Act: -0.0000

Data Index: 948391 (The Pile)

Max Activating Token Index: 376

Text #7

Max Range: 0.5218. Min Range: -0.5218

Max Act: 0.4395. Min Act: -0.0001

Data Index: 1127515 (The Pile)

Max Activating Token Index: 1001

Text #8

Max Range: 0.5218. Min Range: -0.5218

Max Act: 0.4601. Min Act: -0.0001

Data Index: 913545 (The Pile)

Max Activating Token Index: 52

Text #9

Max Range: 0.5218. Min Range: -0.5218

Max Act: 0.4704. Min Act: -0.0000

Data Index: 652834 (The Pile)

Max Activating Token Index: 357

Text #10

Max Range: 0.5218. Min Range: -0.5218

Max Act: 0.4219. Min Act: -0.0000

Data Index: 1894058 (The Pile)

Max Activating Token Index: 845

Text #11

Max Range: 0.5218. Min Range: -0.5218

Max Act: 0.4506. Min Act: -0.0000

Data Index: 1139649 (The Pile)

Max Activating Token Index: 1005

Text #12

Max Range: 0.5218. Min Range: -0.5218

Max Act: 0.4287. Min Act: -0.0000

Data Index: 661900 (The Pile)

Max Activating Token Index: 674

Text #13

Max Range: 0.5218. Min Range: -0.5218

Max Act: 0.4361. Min Act: -0.0000

Data Index: 1179431 (The Pile)

Max Activating Token Index: 40

Text #14

Max Range: 0.5218. Min Range: -0.5218

Max Act: 0.4262. Min Act: -0.0000

Data Index: 1350235 (The Pile)

Max Activating Token Index: 117

Text #15

Max Range: 0.5218. Min Range: -0.5218

Max Act: 0.4369. Min Act: -0.0000

Data Index: 990383 (The Pile)

Max Activating Token Index: 687

Text #16

Max Range: 0.5218. Min Range: -0.5218

Max Act: 0.4080. Min Act: -0.0000

Data Index: 972024 (The Pile)

Max Activating Token Index: 884

Text #17

Max Range: 0.5218. Min Range: -0.5218

Max Act: 0.4437. Min Act: -0.0000

Data Index: 1677056 (The Pile)

Max Activating Token Index: 995

Text #18

Max Range: 0.5218. Min Range: -0.5218

Max Act: 0.4468. Min Act: -0.0000

Data Index: 102846 (The Pile)

Max Activating Token Index: 924

Text #19

Max Range: 0.5218. Min Range: -0.5218

Max Act: 0.3613. Min Act: -0.0000

Data Index: 1473380 (The Pile)

Max Activating Token Index: 1005