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

Dataset: The Pile

Neuron 3890 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: 0.3552. Min Range: -0.3552

Max Act: 0.3552. Min Act: -0.0000

Data Index: 187924 (The Pile)

Max Activating Token Index: 69

Text #1

Max Range: 0.3552. Min Range: -0.3552

Max Act: 0.2982. Min Act: -0.0000

Data Index: 1301306 (The Pile)

Max Activating Token Index: 845

Text #2

Max Range: 0.3552. Min Range: -0.3552

Max Act: 0.3141. Min Act: -0.0000

Data Index: 197376 (The Pile)

Max Activating Token Index: 233

Text #3

Max Range: 0.3552. Min Range: -0.3552

Max Act: 0.3049. Min Act: -0.0000

Data Index: 1244853 (The Pile)

Max Activating Token Index: 691

Text #4

Max Range: 0.3552. Min Range: -0.3552

Max Act: 0.2593. Min Act: -0.0000

Data Index: 1571851 (The Pile)

Max Activating Token Index: 607

Text #5

Max Range: 0.3552. Min Range: -0.3552

Max Act: 0.2968. Min Act: -0.0000

Data Index: 1173174 (The Pile)

Max Activating Token Index: 248

Text #6

Max Range: 0.3552. Min Range: -0.3552

Max Act: 0.2817. Min Act: -0.0000

Data Index: 407454 (The Pile)

Max Activating Token Index: 136

Text #7

Max Range: 0.3552. Min Range: -0.3552

Max Act: 0.2756. Min Act: -0.0000

Data Index: 761683 (The Pile)

Max Activating Token Index: 152

Text #8

Max Range: 0.3552. Min Range: -0.3552

Max Act: 0.2766. Min Act: -0.0000

Data Index: 701152 (The Pile)

Max Activating Token Index: 734

Text #9

Max Range: 0.3552. Min Range: -0.3552

Max Act: 0.3028. Min Act: -0.0000

Data Index: 761129 (The Pile)

Max Activating Token Index: 433

Text #10

Max Range: 0.3552. Min Range: -0.3552

Max Act: 0.2778. Min Act: -0.0000

Data Index: 39064 (The Pile)

Max Activating Token Index: 115

Text #11

Max Range: 0.3552. Min Range: -0.3552

Max Act: 0.2492. Min Act: -0.0000

Data Index: 1391702 (The Pile)

Max Activating Token Index: 786

Text #12

Max Range: 0.3552. Min Range: -0.3552

Max Act: 0.2543. Min Act: -0.0000

Data Index: 1401386 (The Pile)

Max Activating Token Index: 533

Text #13

Max Range: 0.3552. Min Range: -0.3552

Max Act: 0.2575. Min Act: -0.0000

Data Index: 975668 (The Pile)

Max Activating Token Index: 892

Text #14

Max Range: 0.3552. Min Range: -0.3552

Max Act: 0.2650. Min Act: -0.0000

Data Index: 308969 (The Pile)

Max Activating Token Index: 875

Text #15

Max Range: 0.3552. Min Range: -0.3552

Max Act: 0.2471. Min Act: -0.0000

Data Index: 1809581 (The Pile)

Max Activating Token Index: 694

Text #16

Max Range: 0.3552. Min Range: -0.3552

Max Act: 0.2610. Min Act: -0.0000

Data Index: 1389291 (The Pile)

Max Activating Token Index: 54

Text #17

Max Range: 0.3552. Min Range: -0.3552

Max Act: 0.2577. Min Act: -0.0000

Data Index: 53969 (The Pile)

Max Activating Token Index: 181

Text #18

Max Range: 0.3552. Min Range: -0.3552

Max Act: 0.2466. Min Act: -0.0000

Data Index: 731253 (The Pile)

Max Activating Token Index: 485

Text #19

Max Range: 0.3552. Min Range: -0.3552

Max Act: 0.2498. Min Act: -0.0000

Data Index: 489343 (The Pile)

Max Activating Token Index: 48