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

Dataset: The Pile

Neuron 1358 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9797. Min Range: -0.9797

Max Act: 0.9797. Min Act: -0.0000

Data Index: 1493943 (The Pile)

Max Activating Token Index: 1018

Text #1

Max Range: 0.9797. Min Range: -0.9797

Max Act: 0.8394. Min Act: -0.0000

Data Index: 1086384 (The Pile)

Max Activating Token Index: 838

Text #2

Max Range: 0.9797. Min Range: -0.9797

Max Act: 0.7787. Min Act: -0.0000

Data Index: 1160952 (The Pile)

Max Activating Token Index: 11

Text #3

Max Range: 0.9797. Min Range: -0.9797

Max Act: 0.8191. Min Act: -0.0000

Data Index: 1527557 (The Pile)

Max Activating Token Index: 233

Text #4

Max Range: 0.9797. Min Range: -0.9797

Max Act: 0.8060. Min Act: -0.0000

Data Index: 513922 (The Pile)

Max Activating Token Index: 11

Text #5

Max Range: 0.9797. Min Range: -0.9797

Max Act: 0.7536. Min Act: -0.0000

Data Index: 1943311 (The Pile)

Max Activating Token Index: 695

Text #6

Max Range: 0.9797. Min Range: -0.9797

Max Act: 0.7567. Min Act: -0.0000

Data Index: 234834 (The Pile)

Max Activating Token Index: 641

Text #7

Max Range: 0.9797. Min Range: -0.9797

Max Act: 0.6993. Min Act: -0.0000

Data Index: 697103 (The Pile)

Max Activating Token Index: 435

Text #8

Max Range: 0.9797. Min Range: -0.9797

Max Act: 0.6924. Min Act: -0.0000

Data Index: 262745 (The Pile)

Max Activating Token Index: 605

Text #9

Max Range: 0.9797. Min Range: -0.9797

Max Act: 0.7343. Min Act: -0.0000

Data Index: 1784750 (The Pile)

Max Activating Token Index: 886

Text #10

Max Range: 0.9797. Min Range: -0.9797

Max Act: 0.7079. Min Act: -0.0000

Data Index: 408367 (The Pile)

Max Activating Token Index: 22

Text #11

Max Range: 0.9797. Min Range: -0.9797

Max Act: 0.7161. Min Act: -0.0000

Data Index: 214111 (The Pile)

Max Activating Token Index: 462

Text #12

Max Range: 0.9797. Min Range: -0.9797

Max Act: 0.6875. Min Act: -0.0000

Data Index: 550757 (The Pile)

Max Activating Token Index: 7

Text #13

Max Range: 0.9797. Min Range: -0.9797

Max Act: 0.6657. Min Act: -0.0000

Data Index: 605366 (The Pile)

Max Activating Token Index: 741

Text #14

Max Range: 0.9797. Min Range: -0.9797

Max Act: 0.6805. Min Act: -0.0000

Data Index: 1510925 (The Pile)

Max Activating Token Index: 10

Text #15

Max Range: 0.9797. Min Range: -0.9797

Max Act: 0.6401. Min Act: -0.0000

Data Index: 246836 (The Pile)

Max Activating Token Index: 264

Text #16

Max Range: 0.9797. Min Range: -0.9797

Max Act: 0.6961. Min Act: -0.0000

Data Index: 865098 (The Pile)

Max Activating Token Index: 14

Text #17

Max Range: 0.9797. Min Range: -0.9797

Max Act: 0.6407. Min Act: -0.0000

Data Index: 1341704 (The Pile)

Max Activating Token Index: 897

Text #18

Max Range: 0.9797. Min Range: -0.9797

Max Act: 0.6900. Min Act: -0.0000

Data Index: 1027734 (The Pile)

Max Activating Token Index: 80

Text #19

Max Range: 0.9797. Min Range: -0.9797

Max Act: 0.6662. Min Act: -0.0000

Data Index: 276885 (The Pile)

Max Activating Token Index: 908