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

Dataset: The Pile

Neuron 2050 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: 0.5942. Min Range: -0.5942

Max Act: 0.5667. Min Act: -0.0000

Data Index: 1133751 (The Pile)

Max Activating Token Index: 559

Text #1

Max Range: 0.5942. Min Range: -0.5942

Max Act: 0.5942. Min Act: -0.0000

Data Index: 73453 (The Pile)

Max Activating Token Index: 958

Text #2

Max Range: 0.5942. Min Range: -0.5942

Max Act: 0.5777. Min Act: -0.0000

Data Index: 558329 (The Pile)

Max Activating Token Index: 633

Text #3

Max Range: 0.5942. Min Range: -0.5942

Max Act: 0.5884. Min Act: -0.0000

Data Index: 842184 (The Pile)

Max Activating Token Index: 691

Text #4

Max Range: 0.5942. Min Range: -0.5942

Max Act: 0.5752. Min Act: -0.0000

Data Index: 1288111 (The Pile)

Max Activating Token Index: 865

Text #5

Max Range: 0.5942. Min Range: -0.5942

Max Act: 0.5284. Min Act: -0.0000

Data Index: 1808667 (The Pile)

Max Activating Token Index: 927

Text #6

Max Range: 0.5942. Min Range: -0.5942

Max Act: 0.5041. Min Act: -0.0000

Data Index: 1400601 (The Pile)

Max Activating Token Index: 755

Text #7

Max Range: 0.5942. Min Range: -0.5942

Max Act: 0.5182. Min Act: -0.0000

Data Index: 1820711 (The Pile)

Max Activating Token Index: 193

Text #8

Max Range: 0.5942. Min Range: -0.5942

Max Act: 0.5445. Min Act: -0.0000

Data Index: 336854 (The Pile)

Max Activating Token Index: 127

Text #9

Max Range: 0.5942. Min Range: -0.5942

Max Act: 0.4858. Min Act: -0.0000

Data Index: 1402389 (The Pile)

Max Activating Token Index: 864

Text #10

Max Range: 0.5942. Min Range: -0.5942

Max Act: 0.4851. Min Act: -0.0000

Data Index: 291230 (The Pile)

Max Activating Token Index: 373

Text #11

Max Range: 0.5942. Min Range: -0.5942

Max Act: 0.4787. Min Act: -0.0000

Data Index: 249727 (The Pile)

Max Activating Token Index: 761

Text #12

Max Range: 0.5942. Min Range: -0.5942

Max Act: 0.5254. Min Act: -0.0000

Data Index: 414753 (The Pile)

Max Activating Token Index: 983

Text #13

Max Range: 0.5942. Min Range: -0.5942

Max Act: 0.4901. Min Act: -0.0000

Data Index: 375135 (The Pile)

Max Activating Token Index: 964

Text #14

Max Range: 0.5942. Min Range: -0.5942

Max Act: 0.4904. Min Act: -0.0000

Data Index: 1368844 (The Pile)

Max Activating Token Index: 460

Text #15

Max Range: 0.5942. Min Range: -0.5942

Max Act: 0.4909. Min Act: -0.0000

Data Index: 1328703 (The Pile)

Max Activating Token Index: 557

Text #16

Max Range: 0.5942. Min Range: -0.5942

Max Act: 0.5001. Min Act: -0.0000

Data Index: 1062259 (The Pile)

Max Activating Token Index: 573

Text #17

Max Range: 0.5942. Min Range: -0.5942

Max Act: 0.4920. Min Act: -0.0000

Data Index: 1904113 (The Pile)

Max Activating Token Index: 637

Text #18

Max Range: 0.5942. Min Range: -0.5942

Max Act: 0.4951. Min Act: -0.0000

Data Index: 126870 (The Pile)

Max Activating Token Index: 744

Text #19

Max Range: 0.5942. Min Range: -0.5942

Max Act: 0.4742. Min Act: -0.0000

Data Index: 719911 (The Pile)

Max Activating Token Index: 925