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

Dataset: The Pile

Neuron 2306 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: 0.4722. Min Range: -0.4722

Max Act: 0.4722. Min Act: -0.0000

Data Index: 1339361 (The Pile)

Max Activating Token Index: 755

Text #1

Max Range: 0.4722. Min Range: -0.4722

Max Act: 0.3894. Min Act: -0.0000

Data Index: 1135554 (The Pile)

Max Activating Token Index: 241

Text #2

Max Range: 0.4722. Min Range: -0.4722

Max Act: 0.3964. Min Act: -0.0000

Data Index: 223642 (The Pile)

Max Activating Token Index: 281

Text #3

Max Range: 0.4722. Min Range: -0.4722

Max Act: 0.3854. Min Act: -0.0000

Data Index: 428906 (The Pile)

Max Activating Token Index: 502

Text #4

Max Range: 0.4722. Min Range: -0.4722

Max Act: 0.4268. Min Act: -0.0000

Data Index: 1654341 (The Pile)

Max Activating Token Index: 847

Text #5

Max Range: 0.4722. Min Range: -0.4722

Max Act: 0.3807. Min Act: -0.0000

Data Index: 1205947 (The Pile)

Max Activating Token Index: 1014

Text #6

Max Range: 0.4722. Min Range: -0.4722

Max Act: 0.3612. Min Act: -0.0000

Data Index: 378720 (The Pile)

Max Activating Token Index: 360

Text #7

Max Range: 0.4722. Min Range: -0.4722

Max Act: 0.3560. Min Act: -0.0000

Data Index: 1030655 (The Pile)

Max Activating Token Index: 523

Text #8

Max Range: 0.4722. Min Range: -0.4722

Max Act: 0.3417. Min Act: -0.0000

Data Index: 1711087 (The Pile)

Max Activating Token Index: 612

Text #9

Max Range: 0.4722. Min Range: -0.4722

Max Act: 0.3713. Min Act: -0.0000

Data Index: 1210974 (The Pile)

Max Activating Token Index: 230

Text #10

Max Range: 0.4722. Min Range: -0.4722

Max Act: 0.3518. Min Act: -0.0000

Data Index: 1190877 (The Pile)

Max Activating Token Index: 679

Text #11

Max Range: 0.4722. Min Range: -0.4722

Max Act: 0.3327. Min Act: -0.0000

Data Index: 1367367 (The Pile)

Max Activating Token Index: 343

Text #12

Max Range: 0.4722. Min Range: -0.4722

Max Act: 0.3186. Min Act: -0.0000

Data Index: 1759542 (The Pile)

Max Activating Token Index: 943

Text #13

Max Range: 0.4722. Min Range: -0.4722

Max Act: 0.3413. Min Act: -0.0000

Data Index: 53760 (The Pile)

Max Activating Token Index: 574

Text #14

Max Range: 0.4722. Min Range: -0.4722

Max Act: 0.3244. Min Act: -0.0000

Data Index: 851457 (The Pile)

Max Activating Token Index: 556

Text #15

Max Range: 0.4722. Min Range: -0.4722

Max Act: 0.2984. Min Act: -0.0000

Data Index: 1191070 (The Pile)

Max Activating Token Index: 513

Text #16

Max Range: 0.4722. Min Range: -0.4722

Max Act: 0.2865. Min Act: -0.0000

Data Index: 953176 (The Pile)

Max Activating Token Index: 831

Text #17

Max Range: 0.4722. Min Range: -0.4722

Max Act: 0.2763. Min Act: -0.0000

Data Index: 1920116 (The Pile)

Max Activating Token Index: 566

Text #18

Max Range: 0.4722. Min Range: -0.4722

Max Act: 0.2935. Min Act: -0.0000

Data Index: 1535777 (The Pile)

Max Activating Token Index: 488

Text #19

Max Range: 0.4722. Min Range: -0.4722

Max Act: 0.2939. Min Act: -0.0000

Data Index: 1691202 (The Pile)

Max Activating Token Index: 83