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

Dataset: The Pile

Neuron 1892 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.8921. Min Range: -0.8921

Max Act: 0.8921. Min Act: -0.0000

Data Index: 645997 (The Pile)

Max Activating Token Index: 470

Text #1

Max Range: 0.8921. Min Range: -0.8921

Max Act: 0.7791. Min Act: -0.0000

Data Index: 695797 (The Pile)

Max Activating Token Index: 29

Text #2

Max Range: 0.8921. Min Range: -0.8921

Max Act: 0.7918. Min Act: -0.0000

Data Index: 1114977 (The Pile)

Max Activating Token Index: 48

Text #3

Max Range: 0.8921. Min Range: -0.8921

Max Act: 0.6915. Min Act: -0.0000

Data Index: 1408347 (The Pile)

Max Activating Token Index: 102

Text #4

Max Range: 0.8921. Min Range: -0.8921

Max Act: 0.7510. Min Act: -0.0000

Data Index: 1936466 (The Pile)

Max Activating Token Index: 1008

Text #5

Max Range: 0.8921. Min Range: -0.8921

Max Act: 0.7522. Min Act: -0.0000

Data Index: 1020172 (The Pile)

Max Activating Token Index: 741

Text #6

Max Range: 0.8921. Min Range: -0.8921

Max Act: 0.7496. Min Act: -0.0000

Data Index: 221768 (The Pile)

Max Activating Token Index: 255

Text #7

Max Range: 0.8921. Min Range: -0.8921

Max Act: 0.6507. Min Act: -0.0000

Data Index: 55470 (The Pile)

Max Activating Token Index: 1016

Text #8

Max Range: 0.8921. Min Range: -0.8921

Max Act: 0.6988. Min Act: -0.0000

Data Index: 1747055 (The Pile)

Max Activating Token Index: 935

Text #9

Max Range: 0.8921. Min Range: -0.8921

Max Act: 0.7132. Min Act: -0.0000

Data Index: 1719777 (The Pile)

Max Activating Token Index: 132

Text #10

Max Range: 0.8921. Min Range: -0.8921

Max Act: 0.7039. Min Act: -0.0000

Data Index: 80322 (The Pile)

Max Activating Token Index: 365

Text #11

Max Range: 0.8921. Min Range: -0.8921

Max Act: 0.6801. Min Act: -0.0000

Data Index: 551438 (The Pile)

Max Activating Token Index: 521

Text #12

Max Range: 0.8921. Min Range: -0.8921

Max Act: 0.6950. Min Act: -0.0000

Data Index: 1855802 (The Pile)

Max Activating Token Index: 959

Text #13

Max Range: 0.8921. Min Range: -0.8921

Max Act: 0.6231. Min Act: -0.0000

Data Index: 175844 (The Pile)

Max Activating Token Index: 793

Text #14

Max Range: 0.8921. Min Range: -0.8921

Max Act: 0.6518. Min Act: -0.0000

Data Index: 1536822 (The Pile)

Max Activating Token Index: 897

Text #15

Max Range: 0.8921. Min Range: -0.8921

Max Act: 0.6901. Min Act: -0.0000

Data Index: 1234481 (The Pile)

Max Activating Token Index: 33

Text #16

Max Range: 0.8921. Min Range: -0.8921

Max Act: 0.6667. Min Act: -0.0000

Data Index: 914169 (The Pile)

Max Activating Token Index: 82

Text #17

Max Range: 0.8921. Min Range: -0.8921

Max Act: 0.6861. Min Act: -0.0000

Data Index: 92225 (The Pile)

Max Activating Token Index: 268

Text #18

Max Range: 0.8921. Min Range: -0.8921

Max Act: 0.5928. Min Act: -0.0000

Data Index: 1170733 (The Pile)

Max Activating Token Index: 536

Text #19

Max Range: 0.8921. Min Range: -0.8921

Max Act: 0.6312. Min Act: -0.0000

Data Index: 1272682 (The Pile)

Max Activating Token Index: 899