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

Dataset: The Pile

Neuron 813 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3231. Min Range: -0.3231

Max Act: 0.3070. Min Act: -0.0000

Data Index: 249207 (The Pile)

Max Activating Token Index: 555

Text #1

Max Range: 0.3231. Min Range: -0.3231

Max Act: 0.3063. Min Act: -0.0000

Data Index: 1503118 (The Pile)

Max Activating Token Index: 450

Text #2

Max Range: 0.3231. Min Range: -0.3231

Max Act: 0.3215. Min Act: -0.0000

Data Index: 129137 (The Pile)

Max Activating Token Index: 987

Text #3

Max Range: 0.3231. Min Range: -0.3231

Max Act: 0.3086. Min Act: -0.0000

Data Index: 494490 (The Pile)

Max Activating Token Index: 667

Text #4

Max Range: 0.3231. Min Range: -0.3231

Max Act: 0.3231. Min Act: -0.0000

Data Index: 1442977 (The Pile)

Max Activating Token Index: 969

Text #5

Max Range: 0.3231. Min Range: -0.3231

Max Act: 0.3205. Min Act: -0.0000

Data Index: 453631 (The Pile)

Max Activating Token Index: 664

Text #6

Max Range: 0.3231. Min Range: -0.3231

Max Act: 0.2584. Min Act: -0.0000

Data Index: 1626096 (The Pile)

Max Activating Token Index: 991

Text #7

Max Range: 0.3231. Min Range: -0.3231

Max Act: 0.2878. Min Act: -0.0000

Data Index: 1632088 (The Pile)

Max Activating Token Index: 148

Text #8

Max Range: 0.3231. Min Range: -0.3231

Max Act: 0.2621. Min Act: -0.0000

Data Index: 1344025 (The Pile)

Max Activating Token Index: 754

Text #9

Max Range: 0.3231. Min Range: -0.3231

Max Act: 0.2481. Min Act: -0.0000

Data Index: 261088 (The Pile)

Max Activating Token Index: 718

Text #10

Max Range: 0.3231. Min Range: -0.3231

Max Act: 0.2548. Min Act: -0.0000

Data Index: 1723766 (The Pile)

Max Activating Token Index: 202

Text #11

Max Range: 0.3231. Min Range: -0.3231

Max Act: 0.2630. Min Act: -0.0000

Data Index: 913962 (The Pile)

Max Activating Token Index: 609

Text #12

Max Range: 0.3231. Min Range: -0.3231

Max Act: 0.2394. Min Act: -0.0000

Data Index: 1968973 (The Pile)

Max Activating Token Index: 971

Text #13

Max Range: 0.3231. Min Range: -0.3231

Max Act: 0.2492. Min Act: -0.0000

Data Index: 1880642 (The Pile)

Max Activating Token Index: 367

Text #14

Max Range: 0.3231. Min Range: -0.3231

Max Act: 0.2274. Min Act: -0.0000

Data Index: 1728638 (The Pile)

Max Activating Token Index: 846

Text #15

Max Range: 0.3231. Min Range: -0.3231

Max Act: 0.2647. Min Act: -0.0000

Data Index: 1016363 (The Pile)

Max Activating Token Index: 771

Text #16

Max Range: 0.3231. Min Range: -0.3231

Max Act: 0.2686. Min Act: -0.0000

Data Index: 1816867 (The Pile)

Max Activating Token Index: 618

Text #17

Max Range: 0.3231. Min Range: -0.3231

Max Act: 0.2282. Min Act: -0.0000

Data Index: 993428 (The Pile)

Max Activating Token Index: 198

Text #18

Max Range: 0.3231. Min Range: -0.3231

Max Act: 0.2276. Min Act: -0.0000

Data Index: 797619 (The Pile)

Max Activating Token Index: 775

Text #19

Max Range: 0.3231. Min Range: -0.3231

Max Act: 0.1904. Min Act: 0.0000

Data Index: 1073975 (The Pile)

Max Activating Token Index: 809