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

Dataset: The Pile

Neuron 927 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4384. Min Range: -0.4384

Max Act: 0.4013. Min Act: -0.0000

Data Index: 1149828 (The Pile)

Max Activating Token Index: 679

Text #1

Max Range: 0.4384. Min Range: -0.4384

Max Act: 0.4308. Min Act: -0.0000

Data Index: 1447929 (The Pile)

Max Activating Token Index: 808

Text #2

Max Range: 0.4384. Min Range: -0.4384

Max Act: 0.4384. Min Act: -0.0000

Data Index: 312018 (The Pile)

Max Activating Token Index: 435

Text #3

Max Range: 0.4384. Min Range: -0.4384

Max Act: 0.3683. Min Act: -0.0000

Data Index: 21370 (The Pile)

Max Activating Token Index: 798

Text #4

Max Range: 0.4384. Min Range: -0.4384

Max Act: 0.3850. Min Act: -0.0000

Data Index: 493153 (The Pile)

Max Activating Token Index: 783

Text #5

Max Range: 0.4384. Min Range: -0.4384

Max Act: 0.3853. Min Act: -0.0000

Data Index: 1157873 (The Pile)

Max Activating Token Index: 840

Text #6

Max Range: 0.4384. Min Range: -0.4384

Max Act: 0.3702. Min Act: -0.0000

Data Index: 1092069 (The Pile)

Max Activating Token Index: 1018

Text #7

Max Range: 0.4384. Min Range: -0.4384

Max Act: 0.3291. Min Act: -0.0000

Data Index: 1742467 (The Pile)

Max Activating Token Index: 646

Text #8

Max Range: 0.4384. Min Range: -0.4384

Max Act: 0.3912. Min Act: -0.0000

Data Index: 913953 (The Pile)

Max Activating Token Index: 785

Text #9

Max Range: 0.4384. Min Range: -0.4384

Max Act: 0.3553. Min Act: -0.0000

Data Index: 793237 (The Pile)

Max Activating Token Index: 723

Text #10

Max Range: 0.4384. Min Range: -0.4384

Max Act: 0.3879. Min Act: -0.0000

Data Index: 51743 (The Pile)

Max Activating Token Index: 320

Text #11

Max Range: 0.4384. Min Range: -0.4384

Max Act: 0.3878. Min Act: -0.0000

Data Index: 629003 (The Pile)

Max Activating Token Index: 757

Text #12

Max Range: 0.4384. Min Range: -0.4384

Max Act: 0.3230. Min Act: -0.0000

Data Index: 356910 (The Pile)

Max Activating Token Index: 905

Text #13

Max Range: 0.4384. Min Range: -0.4384

Max Act: 0.3589. Min Act: -0.0000

Data Index: 615849 (The Pile)

Max Activating Token Index: 808

Text #14

Max Range: 0.4384. Min Range: -0.4384

Max Act: 0.3945. Min Act: -0.0000

Data Index: 872120 (The Pile)

Max Activating Token Index: 902

Text #15

Max Range: 0.4384. Min Range: -0.4384

Max Act: 0.3489. Min Act: -0.0000

Data Index: 821162 (The Pile)

Max Activating Token Index: 460

Text #16

Max Range: 0.4384. Min Range: -0.4384

Max Act: 0.2912. Min Act: -0.0000

Data Index: 447805 (The Pile)

Max Activating Token Index: 761

Text #17

Max Range: 0.4384. Min Range: -0.4384

Max Act: 0.3723. Min Act: -0.0000

Data Index: 1966631 (The Pile)

Max Activating Token Index: 935

Text #18

Max Range: 0.4384. Min Range: -0.4384

Max Act: 0.3070. Min Act: -0.0000

Data Index: 1089309 (The Pile)

Max Activating Token Index: 814

Text #19

Max Range: 0.4384. Min Range: -0.4384

Max Act: 0.3180. Min Act: -0.0000

Data Index: 1477057 (The Pile)

Max Activating Token Index: 626