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

Dataset: The Pile

Neuron 1465 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: 1.3529. Min Range: -1.3529

Max Act: 1.2702. Min Act: -0.0000

Data Index: 725564 (The Pile)

Max Activating Token Index: 967

Text #1

Max Range: 1.3529. Min Range: -1.3529

Max Act: 1.3529. Min Act: -0.0000

Data Index: 1953146 (The Pile)

Max Activating Token Index: 11

Text #2

Max Range: 1.3529. Min Range: -1.3529

Max Act: 1.1562. Min Act: -0.0000

Data Index: 250436 (The Pile)

Max Activating Token Index: 242

Text #3

Max Range: 1.3529. Min Range: -1.3529

Max Act: 1.1752. Min Act: -0.0000

Data Index: 1803620 (The Pile)

Max Activating Token Index: 14

Text #4

Max Range: 1.3529. Min Range: -1.3529

Max Act: 1.0662. Min Act: -0.0000

Data Index: 1589444 (The Pile)

Max Activating Token Index: 953

Text #5

Max Range: 1.3529. Min Range: -1.3529

Max Act: 1.0738. Min Act: -0.0000

Data Index: 1103808 (The Pile)

Max Activating Token Index: 13

Text #6

Max Range: 1.3529. Min Range: -1.3529

Max Act: 1.0197. Min Act: -0.0000

Data Index: 1906883 (The Pile)

Max Activating Token Index: 176

Text #7

Max Range: 1.3529. Min Range: -1.3529

Max Act: 1.1120. Min Act: -0.0000

Data Index: 263215 (The Pile)

Max Activating Token Index: 964

Text #8

Max Range: 1.3529. Min Range: -1.3529

Max Act: 0.9502. Min Act: -0.0000

Data Index: 800444 (The Pile)

Max Activating Token Index: 927

Text #9

Max Range: 1.3529. Min Range: -1.3529

Max Act: 0.8777. Min Act: -0.0000

Data Index: 670115 (The Pile)

Max Activating Token Index: 957

Text #10

Max Range: 1.3529. Min Range: -1.3529

Max Act: 0.9646. Min Act: -0.0000

Data Index: 1051106 (The Pile)

Max Activating Token Index: 1010

Text #11

Max Range: 1.3529. Min Range: -1.3529

Max Act: 0.9552. Min Act: -0.0000

Data Index: 604896 (The Pile)

Max Activating Token Index: 14

Text #12

Max Range: 1.3529. Min Range: -1.3529

Max Act: 0.9883. Min Act: -0.0000

Data Index: 365087 (The Pile)

Max Activating Token Index: 306

Text #13

Max Range: 1.3529. Min Range: -1.3529

Max Act: 1.0244. Min Act: -0.0000

Data Index: 770220 (The Pile)

Max Activating Token Index: 12

Text #14

Max Range: 1.3529. Min Range: -1.3529

Max Act: 1.0042. Min Act: -0.0000

Data Index: 1792772 (The Pile)

Max Activating Token Index: 11

Text #15

Max Range: 1.3529. Min Range: -1.3529

Max Act: 0.9573. Min Act: -0.0000

Data Index: 1488992 (The Pile)

Max Activating Token Index: 1022

Text #16

Max Range: 1.3529. Min Range: -1.3529

Max Act: 0.9806. Min Act: -0.0000

Data Index: 1249402 (The Pile)

Max Activating Token Index: 348

Text #17

Max Range: 1.3529. Min Range: -1.3529

Max Act: 0.9665. Min Act: -0.0001

Data Index: 1957394 (The Pile)

Max Activating Token Index: 870

Text #18

Max Range: 1.3529. Min Range: -1.3529

Max Act: 0.8824. Min Act: -0.0000

Data Index: 66510 (The Pile)

Max Activating Token Index: 906

Text #19

Max Range: 1.3529. Min Range: -1.3529

Max Act: 0.9446. Min Act: -0.0000

Data Index: 1388907 (The Pile)

Max Activating Token Index: 389