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

Dataset: The Pile

Neuron 3782 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: 0.9402. Min Range: -0.9402

Max Act: 0.9402. Min Act: -0.0000

Data Index: 215425 (The Pile)

Max Activating Token Index: 963

Text #1

Max Range: 0.9402. Min Range: -0.9402

Max Act: 0.9258. Min Act: -0.0000

Data Index: 956656 (The Pile)

Max Activating Token Index: 8

Text #2

Max Range: 0.9402. Min Range: -0.9402

Max Act: 0.8939. Min Act: -0.0000

Data Index: 294216 (The Pile)

Max Activating Token Index: 944

Text #3

Max Range: 0.9402. Min Range: -0.9402

Max Act: 0.8841. Min Act: -0.0000

Data Index: 1561993 (The Pile)

Max Activating Token Index: 54

Text #4

Max Range: 0.9402. Min Range: -0.9402

Max Act: 0.8841. Min Act: -0.0000

Data Index: 1675606 (The Pile)

Max Activating Token Index: 54

Text #5

Max Range: 0.9402. Min Range: -0.9402

Max Act: 0.8961. Min Act: -0.0000

Data Index: 1258893 (The Pile)

Max Activating Token Index: 271

Text #6

Max Range: 0.9402. Min Range: -0.9402

Max Act: 0.9109. Min Act: -0.0000

Data Index: 1922464 (The Pile)

Max Activating Token Index: 1013

Text #7

Max Range: 0.9402. Min Range: -0.9402

Max Act: 0.9179. Min Act: -0.0000

Data Index: 979989 (The Pile)

Max Activating Token Index: 986

Text #8

Max Range: 0.9402. Min Range: -0.9402

Max Act: 0.9356. Min Act: -0.0000

Data Index: 990090 (The Pile)

Max Activating Token Index: 969

Text #9

Max Range: 0.9402. Min Range: -0.9402

Max Act: 0.9057. Min Act: -0.0000

Data Index: 1707247 (The Pile)

Max Activating Token Index: 1011

Text #10

Max Range: 0.9402. Min Range: -0.9402

Max Act: 0.8757. Min Act: -0.0000

Data Index: 1042074 (The Pile)

Max Activating Token Index: 53

Text #11

Max Range: 0.9402. Min Range: -0.9402

Max Act: 0.8327. Min Act: -0.0000

Data Index: 212781 (The Pile)

Max Activating Token Index: 986

Text #12

Max Range: 0.9402. Min Range: -0.9402

Max Act: 0.8267. Min Act: -0.0000

Data Index: 1517214 (The Pile)

Max Activating Token Index: 992

Text #13

Max Range: 0.9402. Min Range: -0.9402

Max Act: 0.8551. Min Act: -0.0001

Data Index: 1873568 (The Pile)

Max Activating Token Index: 655

Text #14

Max Range: 0.9402. Min Range: -0.9402

Max Act: 0.8307. Min Act: -0.0000

Data Index: 1585107 (The Pile)

Max Activating Token Index: 677

Text #15

Max Range: 0.9402. Min Range: -0.9402

Max Act: 0.7992. Min Act: -0.0000

Data Index: 911034 (The Pile)

Max Activating Token Index: 754

Text #16

Max Range: 0.9402. Min Range: -0.9402

Max Act: 0.8427. Min Act: -0.0000

Data Index: 1738145 (The Pile)

Max Activating Token Index: 948

Text #17

Max Range: 0.9402. Min Range: -0.9402

Max Act: 0.8630. Min Act: -0.0000

Data Index: 524712 (The Pile)

Max Activating Token Index: 271

Text #18

Max Range: 0.9402. Min Range: -0.9402

Max Act: 0.8155. Min Act: -0.0001

Data Index: 1084820 (The Pile)

Max Activating Token Index: 553

Text #19

Max Range: 0.9402. Min Range: -0.9402

Max Act: 0.8465. Min Act: -0.0000

Data Index: 1427747 (The Pile)

Max Activating Token Index: 556