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

Dataset: The Pile

Neuron 2651 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3767. Min Range: -0.3767

Max Act: 0.3165. Min Act: -0.0000

Data Index: 253449 (The Pile)

Max Activating Token Index: 613

Text #1

Max Range: 0.3767. Min Range: -0.3767

Max Act: 0.3380. Min Act: -0.0000

Data Index: 185659 (The Pile)

Max Activating Token Index: 986

Text #2

Max Range: 0.3767. Min Range: -0.3767

Max Act: 0.3407. Min Act: -0.0000

Data Index: 1583968 (The Pile)

Max Activating Token Index: 780

Text #3

Max Range: 0.3767. Min Range: -0.3767

Max Act: 0.3767. Min Act: -0.0000

Data Index: 474455 (The Pile)

Max Activating Token Index: 217

Text #4

Max Range: 0.3767. Min Range: -0.3767

Max Act: 0.3411. Min Act: -0.0000

Data Index: 149458 (The Pile)

Max Activating Token Index: 638

Text #5

Max Range: 0.3767. Min Range: -0.3767

Max Act: 0.3360. Min Act: -0.0000

Data Index: 403338 (The Pile)

Max Activating Token Index: 234

Text #6

Max Range: 0.3767. Min Range: -0.3767

Max Act: 0.3136. Min Act: -0.0000

Data Index: 1349389 (The Pile)

Max Activating Token Index: 79

Text #7

Max Range: 0.3767. Min Range: -0.3767

Max Act: 0.3101. Min Act: -0.0000

Data Index: 1486887 (The Pile)

Max Activating Token Index: 767

Text #8

Max Range: 0.3767. Min Range: -0.3767

Max Act: 0.3115. Min Act: -0.0000

Data Index: 1457918 (The Pile)

Max Activating Token Index: 399

Text #9

Max Range: 0.3767. Min Range: -0.3767

Max Act: 0.3244. Min Act: -0.0000

Data Index: 917910 (The Pile)

Max Activating Token Index: 865

Text #10

Max Range: 0.3767. Min Range: -0.3767

Max Act: 0.3182. Min Act: -0.0000

Data Index: 7348 (The Pile)

Max Activating Token Index: 1019

Text #11

Max Range: 0.3767. Min Range: -0.3767

Max Act: 0.2935. Min Act: -0.0000

Data Index: 572620 (The Pile)

Max Activating Token Index: 93

Text #12

Max Range: 0.3767. Min Range: -0.3767

Max Act: 0.3091. Min Act: -0.0000

Data Index: 1894492 (The Pile)

Max Activating Token Index: 222

Text #13

Max Range: 0.3767. Min Range: -0.3767

Max Act: 0.3080. Min Act: -0.0000

Data Index: 284114 (The Pile)

Max Activating Token Index: 330

Text #14

Max Range: 0.3767. Min Range: -0.3767

Max Act: 0.2896. Min Act: -0.0000

Data Index: 1017448 (The Pile)

Max Activating Token Index: 483

Text #15

Max Range: 0.3767. Min Range: -0.3767

Max Act: 0.3001. Min Act: -0.0000

Data Index: 1352035 (The Pile)

Max Activating Token Index: 85

Text #16

Max Range: 0.3767. Min Range: -0.3767

Max Act: 0.2809. Min Act: -0.0000

Data Index: 307832 (The Pile)

Max Activating Token Index: 1007

Text #17

Max Range: 0.3767. Min Range: -0.3767

Max Act: 0.3002. Min Act: -0.0000

Data Index: 629006 (The Pile)

Max Activating Token Index: 265

Text #18

Max Range: 0.3767. Min Range: -0.3767

Max Act: 0.2727. Min Act: -0.0000

Data Index: 1169551 (The Pile)

Max Activating Token Index: 775

Text #19

Max Range: 0.3767. Min Range: -0.3767

Max Act: 0.2786. Min Act: -0.0000

Data Index: 1313648 (The Pile)

Max Activating Token Index: 192