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

Dataset: The Pile

Neuron 1838 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8681. Min Range: -0.8681

Max Act: 0.8681. Min Act: -0.0000

Data Index: 502438 (The Pile)

Max Activating Token Index: 956

Text #1

Max Range: 0.8681. Min Range: -0.8681

Max Act: 0.8244. Min Act: -0.0000

Data Index: 501768 (The Pile)

Max Activating Token Index: 687

Text #2

Max Range: 0.8681. Min Range: -0.8681

Max Act: 0.7952. Min Act: -0.0000

Data Index: 686122 (The Pile)

Max Activating Token Index: 133

Text #3

Max Range: 0.8681. Min Range: -0.8681

Max Act: 0.7345. Min Act: -0.0000

Data Index: 1911374 (The Pile)

Max Activating Token Index: 642

Text #4

Max Range: 0.8681. Min Range: -0.8681

Max Act: 0.7763. Min Act: -0.0000

Data Index: 613153 (The Pile)

Max Activating Token Index: 56

Text #5

Max Range: 0.8681. Min Range: -0.8681

Max Act: 0.7797. Min Act: -0.0000

Data Index: 694592 (The Pile)

Max Activating Token Index: 998

Text #6

Max Range: 0.8681. Min Range: -0.8681

Max Act: 0.6198. Min Act: -0.0000

Data Index: 137622 (The Pile)

Max Activating Token Index: 232

Text #7

Max Range: 0.8681. Min Range: -0.8681

Max Act: 0.7804. Min Act: -0.0000

Data Index: 793135 (The Pile)

Max Activating Token Index: 975

Text #8

Max Range: 0.8681. Min Range: -0.8681

Max Act: 0.6402. Min Act: -0.0000

Data Index: 1860850 (The Pile)

Max Activating Token Index: 568

Text #9

Max Range: 0.8681. Min Range: -0.8681

Max Act: 0.6850. Min Act: -0.0000

Data Index: 192896 (The Pile)

Max Activating Token Index: 59

Text #10

Max Range: 0.8681. Min Range: -0.8681

Max Act: 0.6466. Min Act: -0.0000

Data Index: 1465024 (The Pile)

Max Activating Token Index: 384

Text #11

Max Range: 0.8681. Min Range: -0.8681

Max Act: 0.6431. Min Act: -0.0000

Data Index: 1975347 (The Pile)

Max Activating Token Index: 711

Text #12

Max Range: 0.8681. Min Range: -0.8681

Max Act: 0.6161. Min Act: -0.0000

Data Index: 208047 (The Pile)

Max Activating Token Index: 142

Text #13

Max Range: 0.8681. Min Range: -0.8681

Max Act: 0.7223. Min Act: -0.0000

Data Index: 1134005 (The Pile)

Max Activating Token Index: 401

Text #14

Max Range: 0.8681. Min Range: -0.8681

Max Act: 0.6355. Min Act: -0.0000

Data Index: 1823483 (The Pile)

Max Activating Token Index: 607

Text #15

Max Range: 0.8681. Min Range: -0.8681

Max Act: 0.6465. Min Act: -0.0000

Data Index: 518957 (The Pile)

Max Activating Token Index: 180

Text #16

Max Range: 0.8681. Min Range: -0.8681

Max Act: 0.5838. Min Act: -0.0000

Data Index: 1859653 (The Pile)

Max Activating Token Index: 947

Text #17

Max Range: 0.8681. Min Range: -0.8681

Max Act: 0.5749. Min Act: -0.0000

Data Index: 555782 (The Pile)

Max Activating Token Index: 718

Text #18

Max Range: 0.8681. Min Range: -0.8681

Max Act: 0.6373. Min Act: -0.0000

Data Index: 1891231 (The Pile)

Max Activating Token Index: 504

Text #19

Max Range: 0.8681. Min Range: -0.8681

Max Act: 0.6400. Min Act: -0.0000

Data Index: 1049377 (The Pile)

Max Activating Token Index: 892