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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3668 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9051. Min Range: -1.9051

Max Act: 1.9051. Min Act: -0.0000

Data Index: 48513 (C4 (Web Text))

Max Activating Token Index: 799

Text #1

Max Range: 1.9051. Min Range: -1.9051

Max Act: 1.2502. Min Act: -0.0000

Data Index: 378880 (C4 (Web Text))

Max Activating Token Index: 514

Text #2

Max Range: 1.9051. Min Range: -1.9051

Max Act: 1.2429. Min Act: -0.0000

Data Index: 982153 (C4 (Web Text))

Max Activating Token Index: 453

Text #3

Max Range: 1.9051. Min Range: -1.9051

Max Act: 1.1464. Min Act: -0.0000

Data Index: 1322615 (C4 (Web Text))

Max Activating Token Index: 65

Text #4

Max Range: 1.9051. Min Range: -1.9051

Max Act: 1.1332. Min Act: -0.0000

Data Index: 564050 (C4 (Web Text))

Max Activating Token Index: 545

Text #5

Max Range: 1.9051. Min Range: -1.9051

Max Act: 1.1217. Min Act: -0.0000

Data Index: 15489 (C4 (Web Text))

Max Activating Token Index: 22

Text #6

Max Range: 1.9051. Min Range: -1.9051

Max Act: 1.0016. Min Act: -0.0000

Data Index: 65936 (C4 (Web Text))

Max Activating Token Index: 571

Text #7

Max Range: 1.9051. Min Range: -1.9051

Max Act: 0.9747. Min Act: -0.0000

Data Index: 1334136 (C4 (Web Text))

Max Activating Token Index: 189

Text #8

Max Range: 1.9051. Min Range: -1.9051

Max Act: 1.0079. Min Act: -0.0000

Data Index: 56090 (C4 (Web Text))

Max Activating Token Index: 720

Text #9

Max Range: 1.9051. Min Range: -1.9051

Max Act: 0.9635. Min Act: -0.0000

Data Index: 796445 (C4 (Web Text))

Max Activating Token Index: 394

Text #10

Max Range: 1.9051. Min Range: -1.9051

Max Act: 0.9051. Min Act: -0.0000

Data Index: 691113 (C4 (Web Text))

Max Activating Token Index: 988

Text #11

Max Range: 1.9051. Min Range: -1.9051

Max Act: 0.9849. Min Act: -0.0000

Data Index: 550575 (C4 (Web Text))

Max Activating Token Index: 341

Text #12

Max Range: 1.9051. Min Range: -1.9051

Max Act: 0.9823. Min Act: -0.0000

Data Index: 124261 (C4 (Web Text))

Max Activating Token Index: 115

Text #13

Max Range: 1.9051. Min Range: -1.9051

Max Act: 0.9797. Min Act: -0.0000

Data Index: 867037 (C4 (Web Text))

Max Activating Token Index: 855

Text #14

Max Range: 1.9051. Min Range: -1.9051

Max Act: 0.9222. Min Act: -0.0000

Data Index: 616802 (C4 (Web Text))

Max Activating Token Index: 167

Text #15

Max Range: 1.9051. Min Range: -1.9051

Max Act: 0.8584. Min Act: -0.0000

Data Index: 1210773 (C4 (Web Text))

Max Activating Token Index: 729

Text #16

Max Range: 1.9051. Min Range: -1.9051

Max Act: 1.0186. Min Act: -0.0000

Data Index: 966524 (C4 (Web Text))

Max Activating Token Index: 995

Text #17

Max Range: 1.9051. Min Range: -1.9051

Max Act: 0.9567. Min Act: -0.0000

Data Index: 1193394 (C4 (Web Text))

Max Activating Token Index: 191

Text #18

Max Range: 1.9051. Min Range: -1.9051

Max Act: 0.9464. Min Act: -0.0000

Data Index: 506568 (C4 (Web Text))

Max Activating Token Index: 986

Text #19

Max Range: 1.9051. Min Range: -1.9051

Max Act: 0.9172. Min Act: -0.0000

Data Index: 536334 (C4 (Web Text))

Max Activating Token Index: 74