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

Dataset: The Pile

Neuron 1455 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.9336. Min Range: -0.9336

Max Act: 0.9038. Min Act: -0.0000

Data Index: 1116680 (The Pile)

Max Activating Token Index: 1000

Text #1

Max Range: 0.9336. Min Range: -0.9336

Max Act: 0.8704. Min Act: -0.0000

Data Index: 1893204 (The Pile)

Max Activating Token Index: 955

Text #2

Max Range: 0.9336. Min Range: -0.9336

Max Act: 0.8819. Min Act: -0.0000

Data Index: 1952465 (The Pile)

Max Activating Token Index: 1014

Text #3

Max Range: 0.9336. Min Range: -0.9336

Max Act: 0.8899. Min Act: -0.0000

Data Index: 200688 (The Pile)

Max Activating Token Index: 965

Text #4

Max Range: 0.9336. Min Range: -0.9336

Max Act: 0.8475. Min Act: 0.0000

Data Index: 851477 (The Pile)

Max Activating Token Index: 593

Text #5

Max Range: 0.9336. Min Range: -0.9336

Max Act: 0.9336. Min Act: -0.0000

Data Index: 865682 (The Pile)

Max Activating Token Index: 641

Text #6

Max Range: 0.9336. Min Range: -0.9336

Max Act: 0.8764. Min Act: -0.0000

Data Index: 1493625 (The Pile)

Max Activating Token Index: 375

Text #7

Max Range: 0.9336. Min Range: -0.9336

Max Act: 0.8142. Min Act: -0.0000

Data Index: 1720861 (The Pile)

Max Activating Token Index: 675

Text #8

Max Range: 0.9336. Min Range: -0.9336

Max Act: 0.9032. Min Act: -0.0000

Data Index: 686666 (The Pile)

Max Activating Token Index: 1021

Text #9

Max Range: 0.9336. Min Range: -0.9336

Max Act: 0.8336. Min Act: -0.0000

Data Index: 1369491 (The Pile)

Max Activating Token Index: 839

Text #10

Max Range: 0.9336. Min Range: -0.9336

Max Act: 0.8601. Min Act: -0.0000

Data Index: 1150942 (The Pile)

Max Activating Token Index: 799

Text #11

Max Range: 0.9336. Min Range: -0.9336

Max Act: 0.8708. Min Act: -0.0000

Data Index: 1841562 (The Pile)

Max Activating Token Index: 201

Text #12

Max Range: 0.9336. Min Range: -0.9336

Max Act: 0.7675. Min Act: -0.0000

Data Index: 56625 (The Pile)

Max Activating Token Index: 174

Text #13

Max Range: 0.9336. Min Range: -0.9336

Max Act: 0.7508. Min Act: -0.0000

Data Index: 283469 (The Pile)

Max Activating Token Index: 103

Text #14

Max Range: 0.9336. Min Range: -0.9336

Max Act: 0.7480. Min Act: -0.0000

Data Index: 1852494 (The Pile)

Max Activating Token Index: 920

Text #15

Max Range: 0.9336. Min Range: -0.9336

Max Act: 0.7522. Min Act: -0.0000

Data Index: 617216 (The Pile)

Max Activating Token Index: 885

Text #16

Max Range: 0.9336. Min Range: -0.9336

Max Act: 0.7450. Min Act: 0.0000

Data Index: 935511 (The Pile)

Max Activating Token Index: 576

Text #17

Max Range: 0.9336. Min Range: -0.9336

Max Act: 0.7187. Min Act: -0.0000

Data Index: 1587040 (The Pile)

Max Activating Token Index: 519

Text #18

Max Range: 0.9336. Min Range: -0.9336

Max Act: 0.7218. Min Act: -0.0000

Data Index: 1870290 (The Pile)

Max Activating Token Index: 289

Text #19

Max Range: 0.9336. Min Range: -0.9336

Max Act: 0.7346. Min Act: 0.0000

Data Index: 1366981 (The Pile)

Max Activating Token Index: 663