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

Dataset: The Pile

Neuron 2822 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8430. Min Range: -0.8430

Max Act: 0.8430. Min Act: -0.0000

Data Index: 961100 (The Pile)

Max Activating Token Index: 866

Text #1

Max Range: 0.8430. Min Range: -0.8430

Max Act: 0.8047. Min Act: -0.0000

Data Index: 1241435 (The Pile)

Max Activating Token Index: 409

Text #2

Max Range: 0.8430. Min Range: -0.8430

Max Act: 0.7795. Min Act: -0.0000

Data Index: 1408228 (The Pile)

Max Activating Token Index: 470

Text #3

Max Range: 0.8430. Min Range: -0.8430

Max Act: 0.7997. Min Act: -0.0000

Data Index: 1743329 (The Pile)

Max Activating Token Index: 687

Text #4

Max Range: 0.8430. Min Range: -0.8430

Max Act: 0.7303. Min Act: -0.0000

Data Index: 900896 (The Pile)

Max Activating Token Index: 759

Text #5

Max Range: 0.8430. Min Range: -0.8430

Max Act: 0.7661. Min Act: -0.0000

Data Index: 1460478 (The Pile)

Max Activating Token Index: 709

Text #6

Max Range: 0.8430. Min Range: -0.8430

Max Act: 0.6961. Min Act: -0.0000

Data Index: 569550 (The Pile)

Max Activating Token Index: 633

Text #7

Max Range: 0.8430. Min Range: -0.8430

Max Act: 0.6594. Min Act: -0.0000

Data Index: 1503156 (The Pile)

Max Activating Token Index: 186

Text #8

Max Range: 0.8430. Min Range: -0.8430

Max Act: 0.6743. Min Act: -0.0000

Data Index: 1072265 (The Pile)

Max Activating Token Index: 138

Text #9

Max Range: 0.8430. Min Range: -0.8430

Max Act: 0.6596. Min Act: -0.0000

Data Index: 31132 (The Pile)

Max Activating Token Index: 159

Text #10

Max Range: 0.8430. Min Range: -0.8430

Max Act: 0.6470. Min Act: -0.0000

Data Index: 581590 (The Pile)

Max Activating Token Index: 726

Text #11

Max Range: 0.8430. Min Range: -0.8430

Max Act: 0.6638. Min Act: -0.0000

Data Index: 1275026 (The Pile)

Max Activating Token Index: 679

Text #12

Max Range: 0.8430. Min Range: -0.8430

Max Act: 0.6182. Min Act: -0.0000

Data Index: 215683 (The Pile)

Max Activating Token Index: 284

Text #13

Max Range: 0.8430. Min Range: -0.8430

Max Act: 0.6277. Min Act: -0.0000

Data Index: 263844 (The Pile)

Max Activating Token Index: 726

Text #14

Max Range: 0.8430. Min Range: -0.8430

Max Act: 0.5807. Min Act: -0.0000

Data Index: 46370 (The Pile)

Max Activating Token Index: 705

Text #15

Max Range: 0.8430. Min Range: -0.8430

Max Act: 0.6000. Min Act: -0.0000

Data Index: 665145 (The Pile)

Max Activating Token Index: 717

Text #16

Max Range: 0.8430. Min Range: -0.8430

Max Act: 0.6030. Min Act: -0.0000

Data Index: 49335 (The Pile)

Max Activating Token Index: 781

Text #17

Max Range: 0.8430. Min Range: -0.8430

Max Act: 0.5921. Min Act: -0.0000

Data Index: 1619450 (The Pile)

Max Activating Token Index: 571

Text #18

Max Range: 0.8430. Min Range: -0.8430

Max Act: 0.5975. Min Act: -0.0000

Data Index: 1235472 (The Pile)

Max Activating Token Index: 991

Text #19

Max Range: 0.8430. Min Range: -0.8430

Max Act: 0.6049. Min Act: -0.0000

Data Index: 1680063 (The Pile)

Max Activating Token Index: 218