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

Dataset: The Pile

Neuron 3921 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6457. Min Range: -1.6457

Max Act: 1.4782. Min Act: -0.0000

Data Index: 1359760 (The Pile)

Max Activating Token Index: 598

Text #1

Max Range: 1.6457. Min Range: -1.6457

Max Act: 1.6457. Min Act: -0.0000

Data Index: 1455200 (The Pile)

Max Activating Token Index: 276

Text #2

Max Range: 1.6457. Min Range: -1.6457

Max Act: 1.5786. Min Act: -0.0000

Data Index: 855704 (The Pile)

Max Activating Token Index: 750

Text #3

Max Range: 1.6457. Min Range: -1.6457

Max Act: 1.4546. Min Act: -0.0000

Data Index: 510764 (The Pile)

Max Activating Token Index: 349

Text #4

Max Range: 1.6457. Min Range: -1.6457

Max Act: 1.4276. Min Act: -0.0000

Data Index: 389130 (The Pile)

Max Activating Token Index: 476

Text #5

Max Range: 1.6457. Min Range: -1.6457

Max Act: 1.3447. Min Act: -0.0000

Data Index: 590664 (The Pile)

Max Activating Token Index: 746

Text #6

Max Range: 1.6457. Min Range: -1.6457

Max Act: 1.3091. Min Act: -0.0000

Data Index: 253560 (The Pile)

Max Activating Token Index: 864

Text #7

Max Range: 1.6457. Min Range: -1.6457

Max Act: 1.3461. Min Act: -0.0000

Data Index: 471159 (The Pile)

Max Activating Token Index: 357

Text #8

Max Range: 1.6457. Min Range: -1.6457

Max Act: 1.4520. Min Act: -0.0000

Data Index: 1541397 (The Pile)

Max Activating Token Index: 184

Text #9

Max Range: 1.6457. Min Range: -1.6457

Max Act: 1.3058. Min Act: -0.0000

Data Index: 1764890 (The Pile)

Max Activating Token Index: 819

Text #10

Max Range: 1.6457. Min Range: -1.6457

Max Act: 1.2875. Min Act: -0.0000

Data Index: 436087 (The Pile)

Max Activating Token Index: 826

Text #11

Max Range: 1.6457. Min Range: -1.6457

Max Act: 1.3837. Min Act: -0.0000

Data Index: 1372583 (The Pile)

Max Activating Token Index: 296

Text #12

Max Range: 1.6457. Min Range: -1.6457

Max Act: 1.2954. Min Act: -0.0000

Data Index: 241979 (The Pile)

Max Activating Token Index: 493

Text #13

Max Range: 1.6457. Min Range: -1.6457

Max Act: 1.2855. Min Act: -0.0000

Data Index: 706527 (The Pile)

Max Activating Token Index: 186

Text #14

Max Range: 1.6457. Min Range: -1.6457

Max Act: 1.3357. Min Act: -0.0000

Data Index: 971637 (The Pile)

Max Activating Token Index: 30

Text #15

Max Range: 1.6457. Min Range: -1.6457

Max Act: 1.3309. Min Act: -0.0000

Data Index: 1442839 (The Pile)

Max Activating Token Index: 368

Text #16

Max Range: 1.6457. Min Range: -1.6457

Max Act: 1.1413. Min Act: -0.0000

Data Index: 455102 (The Pile)

Max Activating Token Index: 998

Text #17

Max Range: 1.6457. Min Range: -1.6457

Max Act: 1.2133. Min Act: -0.0000

Data Index: 1043369 (The Pile)

Max Activating Token Index: 106

Text #18

Max Range: 1.6457. Min Range: -1.6457

Max Act: 1.2415. Min Act: -0.0000

Data Index: 1804919 (The Pile)

Max Activating Token Index: 493

Text #19

Max Range: 1.6457. Min Range: -1.6457

Max Act: 1.2857. Min Act: -0.0000

Data Index: 1960371 (The Pile)

Max Activating Token Index: 1000