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

Dataset: The Pile

Neuron 3767 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: 0.7372. Min Range: -0.7372

Max Act: 0.7345. Min Act: -0.0000

Data Index: 462007 (The Pile)

Max Activating Token Index: 962

Text #1

Max Range: 0.7372. Min Range: -0.7372

Max Act: 0.7041. Min Act: -0.0000

Data Index: 830128 (The Pile)

Max Activating Token Index: 714

Text #2

Max Range: 0.7372. Min Range: -0.7372

Max Act: 0.7014. Min Act: -0.0000

Data Index: 1926370 (The Pile)

Max Activating Token Index: 601

Text #3

Max Range: 0.7372. Min Range: -0.7372

Max Act: 0.7372. Min Act: -0.0000

Data Index: 1902564 (The Pile)

Max Activating Token Index: 284

Text #4

Max Range: 0.7372. Min Range: -0.7372

Max Act: 0.6403. Min Act: -0.0000

Data Index: 103942 (The Pile)

Max Activating Token Index: 96

Text #5

Max Range: 0.7372. Min Range: -0.7372

Max Act: 0.6319. Min Act: -0.0000

Data Index: 1581445 (The Pile)

Max Activating Token Index: 94

Text #6

Max Range: 0.7372. Min Range: -0.7372

Max Act: 0.6024. Min Act: -0.0000

Data Index: 1342749 (The Pile)

Max Activating Token Index: 519

Text #7

Max Range: 0.7372. Min Range: -0.7372

Max Act: 0.6174. Min Act: -0.0000

Data Index: 654528 (The Pile)

Max Activating Token Index: 219

Text #8

Max Range: 0.7372. Min Range: -0.7372

Max Act: 0.5944. Min Act: -0.0000

Data Index: 1317399 (The Pile)

Max Activating Token Index: 680

Text #9

Max Range: 0.7372. Min Range: -0.7372

Max Act: 0.5728. Min Act: -0.0000

Data Index: 1354894 (The Pile)

Max Activating Token Index: 797

Text #10

Max Range: 0.7372. Min Range: -0.7372

Max Act: 0.5611. Min Act: -0.0000

Data Index: 1407105 (The Pile)

Max Activating Token Index: 716

Text #11

Max Range: 0.7372. Min Range: -0.7372

Max Act: 0.5933. Min Act: -0.0000

Data Index: 516382 (The Pile)

Max Activating Token Index: 951

Text #12

Max Range: 0.7372. Min Range: -0.7372

Max Act: 0.5951. Min Act: -0.0000

Data Index: 563222 (The Pile)

Max Activating Token Index: 564

Text #13

Max Range: 0.7372. Min Range: -0.7372

Max Act: 0.5653. Min Act: -0.0000

Data Index: 963087 (The Pile)

Max Activating Token Index: 1006

Text #14

Max Range: 0.7372. Min Range: -0.7372

Max Act: 0.5454. Min Act: -0.0000

Data Index: 1077238 (The Pile)

Max Activating Token Index: 392

Text #15

Max Range: 0.7372. Min Range: -0.7372

Max Act: 0.5457. Min Act: -0.0000

Data Index: 1375975 (The Pile)

Max Activating Token Index: 78

Text #16

Max Range: 0.7372. Min Range: -0.7372

Max Act: 0.5689. Min Act: -0.0000

Data Index: 1205302 (The Pile)

Max Activating Token Index: 821

Text #17

Max Range: 0.7372. Min Range: -0.7372

Max Act: 0.5478. Min Act: -0.0000

Data Index: 1413256 (The Pile)

Max Activating Token Index: 332

Text #18

Max Range: 0.7372. Min Range: -0.7372

Max Act: 0.5631. Min Act: -0.0000

Data Index: 684562 (The Pile)

Max Activating Token Index: 60

Text #19

Max Range: 0.7372. Min Range: -0.7372

Max Act: 0.5585. Min Act: -0.0000

Data Index: 898771 (The Pile)

Max Activating Token Index: 51