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

Dataset: The Pile

Neuron 922 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.6758. Min Range: -6.6758

Max Act: 6.6758. Min Act: -0.0000

Data Index: 688603 (The Pile)

Max Activating Token Index: 842

Text #1

Max Range: 6.6758. Min Range: -6.6758

Max Act: 4.7155. Min Act: -0.0000

Data Index: 276672 (The Pile)

Max Activating Token Index: 620

Text #2

Max Range: 6.6758. Min Range: -6.6758

Max Act: 4.6316. Min Act: -0.0000

Data Index: 1187111 (The Pile)

Max Activating Token Index: 439

Text #3

Max Range: 6.6758. Min Range: -6.6758

Max Act: 4.3078. Min Act: -0.0000

Data Index: 1960231 (The Pile)

Max Activating Token Index: 333

Text #4

Max Range: 6.6758. Min Range: -6.6758

Max Act: 3.9603. Min Act: -0.0000

Data Index: 1298234 (The Pile)

Max Activating Token Index: 287

Text #5

Max Range: 6.6758. Min Range: -6.6758

Max Act: 4.4179. Min Act: -0.0000

Data Index: 460827 (The Pile)

Max Activating Token Index: 619

Text #6

Max Range: 6.6758. Min Range: -6.6758

Max Act: 3.9169. Min Act: -0.0000

Data Index: 994539 (The Pile)

Max Activating Token Index: 251

Text #7

Max Range: 6.6758. Min Range: -6.6758

Max Act: 3.8532. Min Act: -0.0000

Data Index: 672942 (The Pile)

Max Activating Token Index: 713

Text #8

Max Range: 6.6758. Min Range: -6.6758

Max Act: 3.8692. Min Act: -0.0000

Data Index: 1998411 (The Pile)

Max Activating Token Index: 429

Text #9

Max Range: 6.6758. Min Range: -6.6758

Max Act: 3.6698. Min Act: -0.0000

Data Index: 1301805 (The Pile)

Max Activating Token Index: 939

Text #10

Max Range: 6.6758. Min Range: -6.6758

Max Act: 3.6363. Min Act: -0.0000

Data Index: 1545612 (The Pile)

Max Activating Token Index: 109

Text #11

Max Range: 6.6758. Min Range: -6.6758

Max Act: 3.1410. Min Act: -0.0000

Data Index: 572531 (The Pile)

Max Activating Token Index: 991

Text #12

Max Range: 6.6758. Min Range: -6.6758

Max Act: 3.5982. Min Act: -0.0000

Data Index: 877115 (The Pile)

Max Activating Token Index: 970

Text #13

Max Range: 6.6758. Min Range: -6.6758

Max Act: 3.3140. Min Act: -0.0000

Data Index: 316242 (The Pile)

Max Activating Token Index: 88

Text #14

Max Range: 6.6758. Min Range: -6.6758

Max Act: 3.1291. Min Act: -0.0000

Data Index: 99182 (The Pile)

Max Activating Token Index: 706

Text #15

Max Range: 6.6758. Min Range: -6.6758

Max Act: 3.2805. Min Act: -0.0000

Data Index: 1959275 (The Pile)

Max Activating Token Index: 733

Text #16

Max Range: 6.6758. Min Range: -6.6758

Max Act: 3.1070. Min Act: -0.0000

Data Index: 1430641 (The Pile)

Max Activating Token Index: 290

Text #17

Max Range: 6.6758. Min Range: -6.6758

Max Act: 3.2239. Min Act: -0.0000

Data Index: 641746 (The Pile)

Max Activating Token Index: 885

Text #18

Max Range: 6.6758. Min Range: -6.6758

Max Act: 3.1958. Min Act: -0.0000

Data Index: 1606544 (The Pile)

Max Activating Token Index: 870

Text #19

Max Range: 6.6758. Min Range: -6.6758

Max Act: 3.0739. Min Act: -0.0000

Data Index: 128726 (The Pile)

Max Activating Token Index: 160