Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2065 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.6514. Min Range: -0.6514

Max Act: 0.6514. Min Act: -0.0000

Data Index: 357781 (The Pile)

Max Activating Token Index: 215

Text #1

Max Range: 0.6514. Min Range: -0.6514

Max Act: 0.6460. Min Act: -0.0000

Data Index: 584491 (The Pile)

Max Activating Token Index: 854

Text #2

Max Range: 0.6514. Min Range: -0.6514

Max Act: 0.5982. Min Act: -0.0000

Data Index: 6173 (The Pile)

Max Activating Token Index: 1009

Text #3

Max Range: 0.6514. Min Range: -0.6514

Max Act: 0.6212. Min Act: -0.0000

Data Index: 967810 (The Pile)

Max Activating Token Index: 776

Text #4

Max Range: 0.6514. Min Range: -0.6514

Max Act: 0.5631. Min Act: -0.0000

Data Index: 1687535 (The Pile)

Max Activating Token Index: 990

Text #5

Max Range: 0.6514. Min Range: -0.6514

Max Act: 0.5921. Min Act: -0.0000

Data Index: 361705 (The Pile)

Max Activating Token Index: 407

Text #6

Max Range: 0.6514. Min Range: -0.6514

Max Act: 0.5510. Min Act: -0.0000

Data Index: 720915 (The Pile)

Max Activating Token Index: 362

Text #7

Max Range: 0.6514. Min Range: -0.6514

Max Act: 0.5540. Min Act: -0.0000

Data Index: 1492583 (The Pile)

Max Activating Token Index: 769

Text #8

Max Range: 0.6514. Min Range: -0.6514

Max Act: 0.5703. Min Act: -0.0000

Data Index: 882289 (The Pile)

Max Activating Token Index: 600

Text #9

Max Range: 0.6514. Min Range: -0.6514

Max Act: 0.5787. Min Act: -0.0000

Data Index: 860683 (The Pile)

Max Activating Token Index: 772

Text #10

Max Range: 0.6514. Min Range: -0.6514

Max Act: 0.5269. Min Act: -0.0000

Data Index: 871061 (The Pile)

Max Activating Token Index: 742

Text #11

Max Range: 0.6514. Min Range: -0.6514

Max Act: 0.4944. Min Act: -0.0000

Data Index: 103342 (The Pile)

Max Activating Token Index: 712

Text #12

Max Range: 0.6514. Min Range: -0.6514

Max Act: 0.4980. Min Act: -0.0000

Data Index: 1898983 (The Pile)

Max Activating Token Index: 766

Text #13

Max Range: 0.6514. Min Range: -0.6514

Max Act: 0.5050. Min Act: -0.0000

Data Index: 1547012 (The Pile)

Max Activating Token Index: 422

Text #14

Max Range: 0.6514. Min Range: -0.6514

Max Act: 0.5002. Min Act: -0.0000

Data Index: 1872674 (The Pile)

Max Activating Token Index: 675

Text #15

Max Range: 0.6514. Min Range: -0.6514

Max Act: 0.4981. Min Act: -0.0000

Data Index: 1855028 (The Pile)

Max Activating Token Index: 365

Text #16

Max Range: 0.6514. Min Range: -0.6514

Max Act: 0.5395. Min Act: -0.0000

Data Index: 1310762 (The Pile)

Max Activating Token Index: 525

Text #17

Max Range: 0.6514. Min Range: -0.6514

Max Act: 0.4943. Min Act: -0.0000

Data Index: 1701803 (The Pile)

Max Activating Token Index: 428

Text #18

Max Range: 0.6514. Min Range: -0.6514

Max Act: 0.4790. Min Act: -0.0000

Data Index: 805526 (The Pile)

Max Activating Token Index: 606

Text #19

Max Range: 0.6514. Min Range: -0.6514

Max Act: 0.5042. Min Act: -0.0000

Data Index: 1464784 (The Pile)

Max Activating Token Index: 643