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

Dataset: The Pile

Neuron 3835 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: 0.3787. Min Range: -0.3787

Max Act: 0.3787. Min Act: -0.0000

Data Index: 652695 (The Pile)

Max Activating Token Index: 332

Text #1

Max Range: 0.3787. Min Range: -0.3787

Max Act: 0.3653. Min Act: -0.0000

Data Index: 180627 (The Pile)

Max Activating Token Index: 410

Text #2

Max Range: 0.3787. Min Range: -0.3787

Max Act: 0.3120. Min Act: -0.0000

Data Index: 1116569 (The Pile)

Max Activating Token Index: 457

Text #3

Max Range: 0.3787. Min Range: -0.3787

Max Act: 0.2999. Min Act: -0.0000

Data Index: 423050 (The Pile)

Max Activating Token Index: 510

Text #4

Max Range: 0.3787. Min Range: -0.3787

Max Act: 0.2900. Min Act: -0.0000

Data Index: 1602801 (The Pile)

Max Activating Token Index: 96

Text #5

Max Range: 0.3787. Min Range: -0.3787

Max Act: 0.2945. Min Act: -0.0000

Data Index: 1292249 (The Pile)

Max Activating Token Index: 930

Text #6

Max Range: 0.3787. Min Range: -0.3787

Max Act: 0.2852. Min Act: -0.0000

Data Index: 1110902 (The Pile)

Max Activating Token Index: 20

Text #7

Max Range: 0.3787. Min Range: -0.3787

Max Act: 0.2728. Min Act: -0.0000

Data Index: 625647 (The Pile)

Max Activating Token Index: 516

Text #8

Max Range: 0.3787. Min Range: -0.3787

Max Act: 0.3000. Min Act: -0.0000

Data Index: 154835 (The Pile)

Max Activating Token Index: 410

Text #9

Max Range: 0.3787. Min Range: -0.3787

Max Act: 0.2689. Min Act: -0.0000

Data Index: 1444834 (The Pile)

Max Activating Token Index: 174

Text #10

Max Range: 0.3787. Min Range: -0.3787

Max Act: 0.2916. Min Act: -0.0000

Data Index: 220946 (The Pile)

Max Activating Token Index: 10

Text #11

Max Range: 0.3787. Min Range: -0.3787

Max Act: 0.2807. Min Act: -0.0000

Data Index: 1342179 (The Pile)

Max Activating Token Index: 726

Text #12

Max Range: 0.3787. Min Range: -0.3787

Max Act: 0.2728. Min Act: -0.0000

Data Index: 1836941 (The Pile)

Max Activating Token Index: 156

Text #13

Max Range: 0.3787. Min Range: -0.3787

Max Act: 0.2882. Min Act: -0.0000

Data Index: 242583 (The Pile)

Max Activating Token Index: 162

Text #14

Max Range: 0.3787. Min Range: -0.3787

Max Act: 0.2788. Min Act: -0.0000

Data Index: 845867 (The Pile)

Max Activating Token Index: 60

Text #15

Max Range: 0.3787. Min Range: -0.3787

Max Act: 0.2961. Min Act: -0.0000

Data Index: 362975 (The Pile)

Max Activating Token Index: 442

Text #16

Max Range: 0.3787. Min Range: -0.3787

Max Act: 0.2824. Min Act: -0.0000

Data Index: 1137173 (The Pile)

Max Activating Token Index: 192

Text #17

Max Range: 0.3787. Min Range: -0.3787

Max Act: 0.2841. Min Act: -0.0000

Data Index: 1355928 (The Pile)

Max Activating Token Index: 788

Text #18

Max Range: 0.3787. Min Range: -0.3787

Max Act: 0.2803. Min Act: -0.0000

Data Index: 229709 (The Pile)

Max Activating Token Index: 124

Text #19

Max Range: 0.3787. Min Range: -0.3787

Max Act: 0.2433. Min Act: -0.0000

Data Index: 1489870 (The Pile)

Max Activating Token Index: 28