Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 4977 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 5.5724. Min Range: -5.5724

Max Act: 5.5724. Min Act: -0.0000

Data Index: 967045 (The Pile)

Max Activating Token Index: 652

Text #1

Max Range: 5.5724. Min Range: -5.5724

Max Act: 5.0016. Min Act: -0.0000

Data Index: 1305434 (The Pile)

Max Activating Token Index: 911

Text #2

Max Range: 5.5724. Min Range: -5.5724

Max Act: 4.7969. Min Act: -0.0000

Data Index: 1249258 (The Pile)

Max Activating Token Index: 666

Text #3

Max Range: 5.5724. Min Range: -5.5724

Max Act: 4.7804. Min Act: -0.0000

Data Index: 1903277 (The Pile)

Max Activating Token Index: 63

Text #4

Max Range: 5.5724. Min Range: -5.5724

Max Act: 4.7565. Min Act: -0.0000

Data Index: 425186 (The Pile)

Max Activating Token Index: 100

Text #5

Max Range: 5.5724. Min Range: -5.5724

Max Act: 4.6281. Min Act: -0.0000

Data Index: 285573 (The Pile)

Max Activating Token Index: 891

Text #6

Max Range: 5.5724. Min Range: -5.5724

Max Act: 4.5490. Min Act: -0.0000

Data Index: 492800 (The Pile)

Max Activating Token Index: 874

Text #7

Max Range: 5.5724. Min Range: -5.5724

Max Act: 4.7554. Min Act: -0.0000

Data Index: 1762745 (The Pile)

Max Activating Token Index: 665

Text #8

Max Range: 5.5724. Min Range: -5.5724

Max Act: 4.1307. Min Act: -0.0000

Data Index: 1203383 (The Pile)

Max Activating Token Index: 182

Text #9

Max Range: 5.5724. Min Range: -5.5724

Max Act: 4.5388. Min Act: -0.0000

Data Index: 1397360 (The Pile)

Max Activating Token Index: 717

Text #10

Max Range: 5.5724. Min Range: -5.5724

Max Act: 4.3100. Min Act: -0.0000

Data Index: 1218166 (The Pile)

Max Activating Token Index: 751

Text #11

Max Range: 5.5724. Min Range: -5.5724

Max Act: 4.2367. Min Act: -0.0000

Data Index: 1823342 (The Pile)

Max Activating Token Index: 1017

Text #12

Max Range: 5.5724. Min Range: -5.5724

Max Act: 4.2974. Min Act: -0.0000

Data Index: 1472828 (The Pile)

Max Activating Token Index: 255

Text #13

Max Range: 5.5724. Min Range: -5.5724

Max Act: 4.2770. Min Act: -0.0000

Data Index: 1904557 (The Pile)

Max Activating Token Index: 468

Text #14

Max Range: 5.5724. Min Range: -5.5724

Max Act: 4.0537. Min Act: -0.0000

Data Index: 1371770 (The Pile)

Max Activating Token Index: 54

Text #15

Max Range: 5.5724. Min Range: -5.5724

Max Act: 4.3453. Min Act: -0.0000

Data Index: 52766 (The Pile)

Max Activating Token Index: 849

Text #16

Max Range: 5.5724. Min Range: -5.5724

Max Act: 4.3773. Min Act: -0.0000

Data Index: 1377604 (The Pile)

Max Activating Token Index: 641

Text #17

Max Range: 5.5724. Min Range: -5.5724

Max Act: 4.3362. Min Act: -0.0000

Data Index: 773216 (The Pile)

Max Activating Token Index: 862

Text #18

Max Range: 5.5724. Min Range: -5.5724

Max Act: 4.1803. Min Act: -0.0000

Data Index: 1180661 (The Pile)

Max Activating Token Index: 746

Text #19

Max Range: 5.5724. Min Range: -5.5724

Max Act: 4.2029. Min Act: -0.0000

Data Index: 165942 (The Pile)

Max Activating Token Index: 963