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

Dataset: The Pile

Neuron 690 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: 1.0429. Min Range: -1.0429

Max Act: 1.0429. Min Act: -0.0000

Data Index: 1888462 (The Pile)

Max Activating Token Index: 219

Text #1

Max Range: 1.0429. Min Range: -1.0429

Max Act: 0.9400. Min Act: -0.0000

Data Index: 280215 (The Pile)

Max Activating Token Index: 370

Text #2

Max Range: 1.0429. Min Range: -1.0429

Max Act: 0.9098. Min Act: -0.0000

Data Index: 1866798 (The Pile)

Max Activating Token Index: 469

Text #3

Max Range: 1.0429. Min Range: -1.0429

Max Act: 0.9072. Min Act: -0.0000

Data Index: 1735652 (The Pile)

Max Activating Token Index: 561

Text #4

Max Range: 1.0429. Min Range: -1.0429

Max Act: 0.9070. Min Act: -0.0000

Data Index: 1100496 (The Pile)

Max Activating Token Index: 130

Text #5

Max Range: 1.0429. Min Range: -1.0429

Max Act: 0.8939. Min Act: -0.0000

Data Index: 726111 (The Pile)

Max Activating Token Index: 822

Text #6

Max Range: 1.0429. Min Range: -1.0429

Max Act: 0.8332. Min Act: -0.0000

Data Index: 34893 (The Pile)

Max Activating Token Index: 514

Text #7

Max Range: 1.0429. Min Range: -1.0429

Max Act: 0.9160. Min Act: -0.0000

Data Index: 32928 (The Pile)

Max Activating Token Index: 49

Text #8

Max Range: 1.0429. Min Range: -1.0429

Max Act: 0.8279. Min Act: -0.0000

Data Index: 278474 (The Pile)

Max Activating Token Index: 407

Text #9

Max Range: 1.0429. Min Range: -1.0429

Max Act: 0.7924. Min Act: -0.0000

Data Index: 871840 (The Pile)

Max Activating Token Index: 706

Text #10

Max Range: 1.0429. Min Range: -1.0429

Max Act: 0.8556. Min Act: -0.0000

Data Index: 705913 (The Pile)

Max Activating Token Index: 622

Text #11

Max Range: 1.0429. Min Range: -1.0429

Max Act: 0.8573. Min Act: -0.0000

Data Index: 960871 (The Pile)

Max Activating Token Index: 815

Text #12

Max Range: 1.0429. Min Range: -1.0429

Max Act: 0.8123. Min Act: -0.0000

Data Index: 1999817 (The Pile)

Max Activating Token Index: 541

Text #13

Max Range: 1.0429. Min Range: -1.0429

Max Act: 0.7837. Min Act: -0.0000

Data Index: 721171 (The Pile)

Max Activating Token Index: 512

Text #14

Max Range: 1.0429. Min Range: -1.0429

Max Act: 0.8514. Min Act: -0.0000

Data Index: 1107511 (The Pile)

Max Activating Token Index: 343

Text #15

Max Range: 1.0429. Min Range: -1.0429

Max Act: 0.7444. Min Act: -0.0000

Data Index: 225168 (The Pile)

Max Activating Token Index: 812

Text #16

Max Range: 1.0429. Min Range: -1.0429

Max Act: 0.8101. Min Act: -0.0000

Data Index: 1836103 (The Pile)

Max Activating Token Index: 957

Text #17

Max Range: 1.0429. Min Range: -1.0429

Max Act: 0.7795. Min Act: -0.0000

Data Index: 1545608 (The Pile)

Max Activating Token Index: 374

Text #18

Max Range: 1.0429. Min Range: -1.0429

Max Act: 0.7592. Min Act: -0.0000

Data Index: 1489610 (The Pile)

Max Activating Token Index: 509

Text #19

Max Range: 1.0429. Min Range: -1.0429

Max Act: 0.7653. Min Act: -0.0000

Data Index: 1815204 (The Pile)

Max Activating Token Index: 591