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

Dataset: The Pile

Neuron 2384 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: 0.6942. Min Range: -0.6942

Max Act: 0.6942. Min Act: -0.0000

Data Index: 358451 (The Pile)

Max Activating Token Index: 986

Text #1

Max Range: 0.6942. Min Range: -0.6942

Max Act: 0.5311. Min Act: -0.0000

Data Index: 1218114 (The Pile)

Max Activating Token Index: 482

Text #2

Max Range: 0.6942. Min Range: -0.6942

Max Act: 0.5023. Min Act: -0.0000

Data Index: 1090008 (The Pile)

Max Activating Token Index: 936

Text #3

Max Range: 0.6942. Min Range: -0.6942

Max Act: 0.4857. Min Act: -0.0000

Data Index: 152417 (The Pile)

Max Activating Token Index: 239

Text #4

Max Range: 0.6942. Min Range: -0.6942

Max Act: 0.4609. Min Act: -0.0000

Data Index: 1942082 (The Pile)

Max Activating Token Index: 842

Text #5

Max Range: 0.6942. Min Range: -0.6942

Max Act: 0.4599. Min Act: -0.0000

Data Index: 944774 (The Pile)

Max Activating Token Index: 549

Text #6

Max Range: 0.6942. Min Range: -0.6942

Max Act: 0.3967. Min Act: -0.0000

Data Index: 196613 (The Pile)

Max Activating Token Index: 850

Text #7

Max Range: 0.6942. Min Range: -0.6942

Max Act: 0.4636. Min Act: -0.0000

Data Index: 381567 (The Pile)

Max Activating Token Index: 550

Text #8

Max Range: 0.6942. Min Range: -0.6942

Max Act: 0.4831. Min Act: -0.0000

Data Index: 1546779 (The Pile)

Max Activating Token Index: 836

Text #9

Max Range: 0.6942. Min Range: -0.6942

Max Act: 0.4311. Min Act: -0.0000

Data Index: 188113 (The Pile)

Max Activating Token Index: 391

Text #10

Max Range: 0.6942. Min Range: -0.6942

Max Act: 0.4642. Min Act: -0.0000

Data Index: 878871 (The Pile)

Max Activating Token Index: 553

Text #11

Max Range: 0.6942. Min Range: -0.6942

Max Act: 0.4707. Min Act: -0.0000

Data Index: 207356 (The Pile)

Max Activating Token Index: 132

Text #12

Max Range: 0.6942. Min Range: -0.6942

Max Act: 0.4435. Min Act: -0.0000

Data Index: 78300 (The Pile)

Max Activating Token Index: 875

Text #13

Max Range: 0.6942. Min Range: -0.6942

Max Act: 0.3829. Min Act: -0.0000

Data Index: 944086 (The Pile)

Max Activating Token Index: 785

Text #14

Max Range: 0.6942. Min Range: -0.6942

Max Act: 0.4824. Min Act: -0.0000

Data Index: 1221747 (The Pile)

Max Activating Token Index: 689

Text #15

Max Range: 0.6942. Min Range: -0.6942

Max Act: 0.4066. Min Act: -0.0000

Data Index: 1252361 (The Pile)

Max Activating Token Index: 960

Text #16

Max Range: 0.6942. Min Range: -0.6942

Max Act: 0.4491. Min Act: -0.0000

Data Index: 598223 (The Pile)

Max Activating Token Index: 35

Text #17

Max Range: 0.6942. Min Range: -0.6942

Max Act: 0.4091. Min Act: -0.0000

Data Index: 1297449 (The Pile)

Max Activating Token Index: 121

Text #18

Max Range: 0.6942. Min Range: -0.6942

Max Act: 0.4502. Min Act: -0.0000

Data Index: 670217 (The Pile)

Max Activating Token Index: 799

Text #19

Max Range: 0.6942. Min Range: -0.6942

Max Act: 0.4151. Min Act: -0.0000

Data Index: 1045617 (The Pile)

Max Activating Token Index: 805