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

Dataset: The Pile

Neuron 130 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0400. Min Act: -0.0000

Data Index: 808376 (The Pile)

Max Activating Token Index: 8

Text #1

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0382. Min Act: -0.0000

Data Index: 851852 (The Pile)

Max Activating Token Index: 11

Text #2

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0377. Min Act: -0.0000

Data Index: 1257098 (The Pile)

Max Activating Token Index: 9

Text #3

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0370. Min Act: -0.0000

Data Index: 882397 (The Pile)

Max Activating Token Index: 12

Text #4

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0378. Min Act: -0.0000

Data Index: 196562 (The Pile)

Max Activating Token Index: 7

Text #5

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0360. Min Act: -0.0000

Data Index: 1934649 (The Pile)

Max Activating Token Index: 165

Text #6

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0359. Min Act: -0.0000

Data Index: 966495 (The Pile)

Max Activating Token Index: 87

Text #7

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0353. Min Act: 0.0000

Data Index: 109712 (The Pile)

Max Activating Token Index: 407

Text #8

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0342. Min Act: 0.0000

Data Index: 905569 (The Pile)

Max Activating Token Index: 8

Text #9

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0341. Min Act: -0.0000

Data Index: 1470536 (The Pile)

Max Activating Token Index: 63

Text #10

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0338. Min Act: 0.0001

Data Index: 229271 (The Pile)

Max Activating Token Index: 157

Text #11

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0337. Min Act: 0.0000

Data Index: 1893748 (The Pile)

Max Activating Token Index: 30

Text #12

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0337. Min Act: -0.0000

Data Index: 615494 (The Pile)

Max Activating Token Index: 21

Text #13

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0337. Min Act: -0.0000

Data Index: 308569 (The Pile)

Max Activating Token Index: 4

Text #14

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0338. Min Act: -0.0000

Data Index: 317666 (The Pile)

Max Activating Token Index: 22

Text #15

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0336. Min Act: -0.0000

Data Index: 722020 (The Pile)

Max Activating Token Index: 5

Text #16

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0334. Min Act: -0.0000

Data Index: 1099421 (The Pile)

Max Activating Token Index: 5

Text #17

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0334. Min Act: 0.0000

Data Index: 1663657 (The Pile)

Max Activating Token Index: 971

Text #18

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0334. Min Act: -0.0000

Data Index: 1199837 (The Pile)

Max Activating Token Index: 4

Text #19

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0333. Min Act: -0.0000

Data Index: 29516 (The Pile)

Max Activating Token Index: 5