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

Dataset: The Pile

Neuron 4641 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: 1.8957. Min Range: -1.8957

Max Act: 1.7758. Min Act: -0.0000

Data Index: 85207 (The Pile)

Max Activating Token Index: 864

Text #1

Max Range: 1.8957. Min Range: -1.8957

Max Act: 1.8957. Min Act: -0.0000

Data Index: 143018 (The Pile)

Max Activating Token Index: 63

Text #2

Max Range: 1.8957. Min Range: -1.8957

Max Act: 1.5595. Min Act: -0.0000

Data Index: 251803 (The Pile)

Max Activating Token Index: 282

Text #3

Max Range: 1.8957. Min Range: -1.8957

Max Act: 1.4830. Min Act: -0.0000

Data Index: 1155167 (The Pile)

Max Activating Token Index: 717

Text #4

Max Range: 1.8957. Min Range: -1.8957

Max Act: 1.4130. Min Act: -0.0000

Data Index: 792450 (The Pile)

Max Activating Token Index: 589

Text #5

Max Range: 1.8957. Min Range: -1.8957

Max Act: 1.4425. Min Act: -0.0000

Data Index: 620316 (The Pile)

Max Activating Token Index: 721

Text #6

Max Range: 1.8957. Min Range: -1.8957

Max Act: 1.2655. Min Act: -0.0000

Data Index: 552596 (The Pile)

Max Activating Token Index: 381

Text #7

Max Range: 1.8957. Min Range: -1.8957

Max Act: 1.2816. Min Act: -0.0000

Data Index: 118020 (The Pile)

Max Activating Token Index: 932

Text #8

Max Range: 1.8957. Min Range: -1.8957

Max Act: 1.2726. Min Act: -0.0000

Data Index: 810837 (The Pile)

Max Activating Token Index: 397

Text #9

Max Range: 1.8957. Min Range: -1.8957

Max Act: 1.3506. Min Act: -0.0000

Data Index: 1467772 (The Pile)

Max Activating Token Index: 990

Text #10

Max Range: 1.8957. Min Range: -1.8957

Max Act: 1.2494. Min Act: -0.0000

Data Index: 825848 (The Pile)

Max Activating Token Index: 887

Text #11

Max Range: 1.8957. Min Range: -1.8957

Max Act: 1.2385. Min Act: -0.0000

Data Index: 1620111 (The Pile)

Max Activating Token Index: 80

Text #12

Max Range: 1.8957. Min Range: -1.8957

Max Act: 1.2411. Min Act: -0.0000

Data Index: 979467 (The Pile)

Max Activating Token Index: 927

Text #13

Max Range: 1.8957. Min Range: -1.8957

Max Act: 1.1665. Min Act: -0.0000

Data Index: 1023035 (The Pile)

Max Activating Token Index: 737

Text #14

Max Range: 1.8957. Min Range: -1.8957

Max Act: 1.2750. Min Act: -0.0000

Data Index: 1737137 (The Pile)

Max Activating Token Index: 885

Text #15

Max Range: 1.8957. Min Range: -1.8957

Max Act: 1.2297. Min Act: -0.0000

Data Index: 1564930 (The Pile)

Max Activating Token Index: 1017

Text #16

Max Range: 1.8957. Min Range: -1.8957

Max Act: 1.2136. Min Act: -0.0000

Data Index: 304893 (The Pile)

Max Activating Token Index: 90

Text #17

Max Range: 1.8957. Min Range: -1.8957

Max Act: 1.1420. Min Act: -0.0000

Data Index: 1302190 (The Pile)

Max Activating Token Index: 923

Text #18

Max Range: 1.8957. Min Range: -1.8957

Max Act: 1.1346. Min Act: -0.0000

Data Index: 1715769 (The Pile)

Max Activating Token Index: 307

Text #19

Max Range: 1.8957. Min Range: -1.8957

Max Act: 1.1155. Min Act: -0.0000

Data Index: 617231 (The Pile)

Max Activating Token Index: 699