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

Dataset: The Pile

Neuron 2056 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9610. Min Range: -0.9610

Max Act: 0.9067. Min Act: 0.0000

Data Index: 1495618 (The Pile)

Max Activating Token Index: 260

Text #1

Max Range: 0.9610. Min Range: -0.9610

Max Act: 0.8975. Min Act: -0.0000

Data Index: 36786 (The Pile)

Max Activating Token Index: 560

Text #2

Max Range: 0.9610. Min Range: -0.9610

Max Act: 0.9520. Min Act: -0.0000

Data Index: 1679421 (The Pile)

Max Activating Token Index: 383

Text #3

Max Range: 0.9610. Min Range: -0.9610

Max Act: 0.9439. Min Act: -0.0000

Data Index: 1947979 (The Pile)

Max Activating Token Index: 919

Text #4

Max Range: 0.9610. Min Range: -0.9610

Max Act: 0.8961. Min Act: -0.0000

Data Index: 553197 (The Pile)

Max Activating Token Index: 622

Text #5

Max Range: 0.9610. Min Range: -0.9610

Max Act: 0.9139. Min Act: -0.0000

Data Index: 127930 (The Pile)

Max Activating Token Index: 574

Text #6

Max Range: 0.9610. Min Range: -0.9610

Max Act: 0.8902. Min Act: -0.0000

Data Index: 525207 (The Pile)

Max Activating Token Index: 996

Text #7

Max Range: 0.9610. Min Range: -0.9610

Max Act: 0.9610. Min Act: -0.0000

Data Index: 1385 (The Pile)

Max Activating Token Index: 209

Text #8

Max Range: 0.9610. Min Range: -0.9610

Max Act: 0.8570. Min Act: -0.0000

Data Index: 1958943 (The Pile)

Max Activating Token Index: 529

Text #9

Max Range: 0.9610. Min Range: -0.9610

Max Act: 0.8395. Min Act: -0.0000

Data Index: 1536289 (The Pile)

Max Activating Token Index: 938

Text #10

Max Range: 0.9610. Min Range: -0.9610

Max Act: 0.9216. Min Act: -0.0000

Data Index: 1913837 (The Pile)

Max Activating Token Index: 892

Text #11

Max Range: 0.9610. Min Range: -0.9610

Max Act: 0.8308. Min Act: -0.0000

Data Index: 1832566 (The Pile)

Max Activating Token Index: 339

Text #12

Max Range: 0.9610. Min Range: -0.9610

Max Act: 0.8046. Min Act: -0.0000

Data Index: 220293 (The Pile)

Max Activating Token Index: 87

Text #13

Max Range: 0.9610. Min Range: -0.9610

Max Act: 0.8008. Min Act: -0.0000

Data Index: 544585 (The Pile)

Max Activating Token Index: 230

Text #14

Max Range: 0.9610. Min Range: -0.9610

Max Act: 0.7746. Min Act: -0.0000

Data Index: 1263927 (The Pile)

Max Activating Token Index: 569

Text #15

Max Range: 0.9610. Min Range: -0.9610

Max Act: 0.7938. Min Act: 0.0001

Data Index: 1170120 (The Pile)

Max Activating Token Index: 995

Text #16

Max Range: 0.9610. Min Range: -0.9610

Max Act: 0.8344. Min Act: -0.0000

Data Index: 1430990 (The Pile)

Max Activating Token Index: 21

Text #17

Max Range: 0.9610. Min Range: -0.9610

Max Act: 0.8075. Min Act: -0.0000

Data Index: 222453 (The Pile)

Max Activating Token Index: 813

Text #18

Max Range: 0.9610. Min Range: -0.9610

Max Act: 0.8015. Min Act: -0.0000

Data Index: 1202898 (The Pile)

Max Activating Token Index: 996

Text #19

Max Range: 0.9610. Min Range: -0.9610

Max Act: 0.8048. Min Act: -0.0000

Data Index: 98408 (The Pile)

Max Activating Token Index: 428