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

Dataset: The Pile

Neuron 3005 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: 1.2925. Min Range: -1.2925

Max Act: 1.2925. Min Act: -0.0000

Data Index: 781990 (The Pile)

Max Activating Token Index: 558

Text #1

Max Range: 1.2925. Min Range: -1.2925

Max Act: 1.1873. Min Act: -0.0000

Data Index: 449382 (The Pile)

Max Activating Token Index: 475

Text #2

Max Range: 1.2925. Min Range: -1.2925

Max Act: 0.9491. Min Act: -0.0000

Data Index: 618930 (The Pile)

Max Activating Token Index: 314

Text #3

Max Range: 1.2925. Min Range: -1.2925

Max Act: 0.7910. Min Act: -0.0000

Data Index: 1996044 (The Pile)

Max Activating Token Index: 478

Text #4

Max Range: 1.2925. Min Range: -1.2925

Max Act: 0.7443. Min Act: -0.0000

Data Index: 987578 (The Pile)

Max Activating Token Index: 921

Text #5

Max Range: 1.2925. Min Range: -1.2925

Max Act: 0.6407. Min Act: -0.0000

Data Index: 1172777 (The Pile)

Max Activating Token Index: 890

Text #6

Max Range: 1.2925. Min Range: -1.2925

Max Act: 0.6414. Min Act: -0.0000

Data Index: 1945941 (The Pile)

Max Activating Token Index: 670

Text #7

Max Range: 1.2925. Min Range: -1.2925

Max Act: 0.6872. Min Act: -0.0000

Data Index: 1087451 (The Pile)

Max Activating Token Index: 177

Text #8

Max Range: 1.2925. Min Range: -1.2925

Max Act: 0.6700. Min Act: -0.0000

Data Index: 751471 (The Pile)

Max Activating Token Index: 530

Text #9

Max Range: 1.2925. Min Range: -1.2925

Max Act: 0.5900. Min Act: -0.0000

Data Index: 371892 (The Pile)

Max Activating Token Index: 633

Text #10

Max Range: 1.2925. Min Range: -1.2925

Max Act: 0.5777. Min Act: -0.0000

Data Index: 1126843 (The Pile)

Max Activating Token Index: 773

Text #11

Max Range: 1.2925. Min Range: -1.2925

Max Act: 0.6595. Min Act: -0.0000

Data Index: 551011 (The Pile)

Max Activating Token Index: 842

Text #12

Max Range: 1.2925. Min Range: -1.2925

Max Act: 0.5970. Min Act: -0.0000

Data Index: 895910 (The Pile)

Max Activating Token Index: 402

Text #13

Max Range: 1.2925. Min Range: -1.2925

Max Act: 0.5858. Min Act: -0.0000

Data Index: 1399371 (The Pile)

Max Activating Token Index: 323

Text #14

Max Range: 1.2925. Min Range: -1.2925

Max Act: 0.6067. Min Act: -0.0000

Data Index: 73569 (The Pile)

Max Activating Token Index: 1001

Text #15

Max Range: 1.2925. Min Range: -1.2925

Max Act: 0.6039. Min Act: -0.0000

Data Index: 851232 (The Pile)

Max Activating Token Index: 838

Text #16

Max Range: 1.2925. Min Range: -1.2925

Max Act: 0.5326. Min Act: -0.0000

Data Index: 413051 (The Pile)

Max Activating Token Index: 951

Text #17

Max Range: 1.2925. Min Range: -1.2925

Max Act: 0.5583. Min Act: -0.0000

Data Index: 542096 (The Pile)

Max Activating Token Index: 481

Text #18

Max Range: 1.2925. Min Range: -1.2925

Max Act: 0.5399. Min Act: -0.0000

Data Index: 1810475 (The Pile)

Max Activating Token Index: 373

Text #19

Max Range: 1.2925. Min Range: -1.2925

Max Act: 0.5336. Min Act: -0.0000

Data Index: 1656034 (The Pile)

Max Activating Token Index: 858