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

Dataset: The Pile

Neuron 1597 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: 1.7986. Min Range: -1.7986

Max Act: 1.7429. Min Act: -0.0000

Data Index: 1469771 (The Pile)

Max Activating Token Index: 475

Text #1

Max Range: 1.7986. Min Range: -1.7986

Max Act: 1.7986. Min Act: -0.0000

Data Index: 1455003 (The Pile)

Max Activating Token Index: 772

Text #2

Max Range: 1.7986. Min Range: -1.7986

Max Act: 1.4349. Min Act: -0.0000

Data Index: 319530 (The Pile)

Max Activating Token Index: 937

Text #3

Max Range: 1.7986. Min Range: -1.7986

Max Act: 1.4722. Min Act: -0.0000

Data Index: 94610 (The Pile)

Max Activating Token Index: 990

Text #4

Max Range: 1.7986. Min Range: -1.7986

Max Act: 1.6640. Min Act: -0.0000

Data Index: 1294496 (The Pile)

Max Activating Token Index: 194

Text #5

Max Range: 1.7986. Min Range: -1.7986

Max Act: 1.7270. Min Act: -0.0000

Data Index: 1689811 (The Pile)

Max Activating Token Index: 699

Text #6

Max Range: 1.7986. Min Range: -1.7986

Max Act: 1.5845. Min Act: -0.0000

Data Index: 579809 (The Pile)

Max Activating Token Index: 195

Text #7

Max Range: 1.7986. Min Range: -1.7986

Max Act: 1.3390. Min Act: -0.0000

Data Index: 30428 (The Pile)

Max Activating Token Index: 1008

Text #8

Max Range: 1.7986. Min Range: -1.7986

Max Act: 1.5048. Min Act: -0.0000

Data Index: 1429436 (The Pile)

Max Activating Token Index: 538

Text #9

Max Range: 1.7986. Min Range: -1.7986

Max Act: 1.5073. Min Act: -0.0000

Data Index: 6307 (The Pile)

Max Activating Token Index: 600

Text #10

Max Range: 1.7986. Min Range: -1.7986

Max Act: 1.5706. Min Act: -0.0000

Data Index: 426517 (The Pile)

Max Activating Token Index: 85

Text #11

Max Range: 1.7986. Min Range: -1.7986

Max Act: 1.5448. Min Act: -0.0000

Data Index: 1906556 (The Pile)

Max Activating Token Index: 206

Text #12

Max Range: 1.7986. Min Range: -1.7986

Max Act: 1.5412. Min Act: -0.0000

Data Index: 793977 (The Pile)

Max Activating Token Index: 1000

Text #13

Max Range: 1.7986. Min Range: -1.7986

Max Act: 1.5337. Min Act: -0.0000

Data Index: 807650 (The Pile)

Max Activating Token Index: 14

Text #14

Max Range: 1.7986. Min Range: -1.7986

Max Act: 1.5202. Min Act: -0.0000

Data Index: 492891 (The Pile)

Max Activating Token Index: 15

Text #15

Max Range: 1.7986. Min Range: -1.7986

Max Act: 1.4976. Min Act: -0.0000

Data Index: 1172030 (The Pile)

Max Activating Token Index: 720

Text #16

Max Range: 1.7986. Min Range: -1.7986

Max Act: 1.3776. Min Act: -0.0000

Data Index: 1671255 (The Pile)

Max Activating Token Index: 43

Text #17

Max Range: 1.7986. Min Range: -1.7986

Max Act: 1.3879. Min Act: -0.0000

Data Index: 1904432 (The Pile)

Max Activating Token Index: 18

Text #18

Max Range: 1.7986. Min Range: -1.7986

Max Act: 1.3782. Min Act: -0.0000

Data Index: 724711 (The Pile)

Max Activating Token Index: 31

Text #19

Max Range: 1.7986. Min Range: -1.7986

Max Act: 1.5543. Min Act: -0.0000

Data Index: 209787 (The Pile)

Max Activating Token Index: 273