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

Dataset: The Pile

Neuron 2338 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: 1.1597. Min Range: -1.1597

Max Act: 1.1597. Min Act: -0.0000

Data Index: 1888260 (The Pile)

Max Activating Token Index: 859

Text #1

Max Range: 1.1597. Min Range: -1.1597

Max Act: 0.9429. Min Act: -0.0000

Data Index: 1403787 (The Pile)

Max Activating Token Index: 891

Text #2

Max Range: 1.1597. Min Range: -1.1597

Max Act: 0.9923. Min Act: -0.0000

Data Index: 841621 (The Pile)

Max Activating Token Index: 931

Text #3

Max Range: 1.1597. Min Range: -1.1597

Max Act: 0.9227. Min Act: -0.0000

Data Index: 631587 (The Pile)

Max Activating Token Index: 43

Text #4

Max Range: 1.1597. Min Range: -1.1597

Max Act: 0.8495. Min Act: -0.0000

Data Index: 1694159 (The Pile)

Max Activating Token Index: 220

Text #5

Max Range: 1.1597. Min Range: -1.1597

Max Act: 0.8492. Min Act: -0.0000

Data Index: 680721 (The Pile)

Max Activating Token Index: 852

Text #6

Max Range: 1.1597. Min Range: -1.1597

Max Act: 0.8395. Min Act: -0.0000

Data Index: 1454866 (The Pile)

Max Activating Token Index: 970

Text #7

Max Range: 1.1597. Min Range: -1.1597

Max Act: 0.8887. Min Act: -0.0000

Data Index: 105785 (The Pile)

Max Activating Token Index: 104

Text #8

Max Range: 1.1597. Min Range: -1.1597

Max Act: 0.8269. Min Act: 0.0000

Data Index: 1250071 (The Pile)

Max Activating Token Index: 654

Text #9

Max Range: 1.1597. Min Range: -1.1597

Max Act: 0.7978. Min Act: -0.0000

Data Index: 1812374 (The Pile)

Max Activating Token Index: 792

Text #10

Max Range: 1.1597. Min Range: -1.1597

Max Act: 0.7773. Min Act: -0.0000

Data Index: 123675 (The Pile)

Max Activating Token Index: 381

Text #11

Max Range: 1.1597. Min Range: -1.1597

Max Act: 0.7735. Min Act: -0.0000

Data Index: 1404158 (The Pile)

Max Activating Token Index: 986

Text #12

Max Range: 1.1597. Min Range: -1.1597

Max Act: 0.7320. Min Act: -0.0000

Data Index: 1538070 (The Pile)

Max Activating Token Index: 871

Text #13

Max Range: 1.1597. Min Range: -1.1597

Max Act: 0.7953. Min Act: -0.0000

Data Index: 65640 (The Pile)

Max Activating Token Index: 971

Text #14

Max Range: 1.1597. Min Range: -1.1597

Max Act: 0.7204. Min Act: -0.0000

Data Index: 748912 (The Pile)

Max Activating Token Index: 705

Text #15

Max Range: 1.1597. Min Range: -1.1597

Max Act: 0.7252. Min Act: -0.0000

Data Index: 200465 (The Pile)

Max Activating Token Index: 985

Text #16

Max Range: 1.1597. Min Range: -1.1597

Max Act: 0.7126. Min Act: -0.0000

Data Index: 307723 (The Pile)

Max Activating Token Index: 996

Text #17

Max Range: 1.1597. Min Range: -1.1597

Max Act: 0.7249. Min Act: -0.0000

Data Index: 369473 (The Pile)

Max Activating Token Index: 497

Text #18

Max Range: 1.1597. Min Range: -1.1597

Max Act: 0.7670. Min Act: -0.0000

Data Index: 77076 (The Pile)

Max Activating Token Index: 104

Text #19

Max Range: 1.1597. Min Range: -1.1597

Max Act: 0.7254. Min Act: -0.0000

Data Index: 15502 (The Pile)

Max Activating Token Index: 107