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

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

Neuron 2669 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: 4.0953. Min Range: -4.0953

Max Act: 4.0953. Min Act: -0.0000

Data Index: 1322218 (C4 (Web Text))

Max Activating Token Index: 373

Text #1

Max Range: 4.0953. Min Range: -4.0953

Max Act: 4.0905. Min Act: -0.0000

Data Index: 697463 (C4 (Web Text))

Max Activating Token Index: 122

Text #2

Max Range: 4.0953. Min Range: -4.0953

Max Act: 3.8056. Min Act: -0.0000

Data Index: 1052580 (C4 (Web Text))

Max Activating Token Index: 129

Text #3

Max Range: 4.0953. Min Range: -4.0953

Max Act: 3.7716. Min Act: -0.0000

Data Index: 1124160 (C4 (Web Text))

Max Activating Token Index: 481

Text #4

Max Range: 4.0953. Min Range: -4.0953

Max Act: 3.7651. Min Act: -0.0000

Data Index: 1029404 (C4 (Web Text))

Max Activating Token Index: 296

Text #5

Max Range: 4.0953. Min Range: -4.0953

Max Act: 3.6560. Min Act: -0.0000

Data Index: 590738 (C4 (Web Text))

Max Activating Token Index: 450

Text #6

Max Range: 4.0953. Min Range: -4.0953

Max Act: 3.6312. Min Act: -0.0000

Data Index: 1024534 (C4 (Web Text))

Max Activating Token Index: 931

Text #7

Max Range: 4.0953. Min Range: -4.0953

Max Act: 3.1180. Min Act: -0.0000

Data Index: 11522 (C4 (Web Text))

Max Activating Token Index: 404

Text #8

Max Range: 4.0953. Min Range: -4.0953

Max Act: 3.0223. Min Act: -0.0000

Data Index: 37538 (C4 (Web Text))

Max Activating Token Index: 710

Text #9

Max Range: 4.0953. Min Range: -4.0953

Max Act: 2.8814. Min Act: -0.0000

Data Index: 1239503 (C4 (Web Text))

Max Activating Token Index: 664

Text #10

Max Range: 4.0953. Min Range: -4.0953

Max Act: 3.4351. Min Act: -0.0000

Data Index: 17396 (C4 (Web Text))

Max Activating Token Index: 664

Text #11

Max Range: 4.0953. Min Range: -4.0953

Max Act: 2.8002. Min Act: -0.0000

Data Index: 1332200 (C4 (Web Text))

Max Activating Token Index: 826

Text #12

Max Range: 4.0953. Min Range: -4.0953

Max Act: 2.6295. Min Act: -0.0000

Data Index: 1278479 (C4 (Web Text))

Max Activating Token Index: 251

Text #13

Max Range: 4.0953. Min Range: -4.0953

Max Act: 2.4115. Min Act: -0.0000

Data Index: 312815 (C4 (Web Text))

Max Activating Token Index: 763

Text #14

Max Range: 4.0953. Min Range: -4.0953

Max Act: 2.5184. Min Act: -0.0000

Data Index: 1064482 (C4 (Web Text))

Max Activating Token Index: 172

Text #15

Max Range: 4.0953. Min Range: -4.0953

Max Act: 2.7809. Min Act: -0.0000

Data Index: 770514 (C4 (Web Text))

Max Activating Token Index: 63

Text #16

Max Range: 4.0953. Min Range: -4.0953

Max Act: 2.6407. Min Act: -0.0000

Data Index: 1075409 (C4 (Web Text))

Max Activating Token Index: 108

Text #17

Max Range: 4.0953. Min Range: -4.0953

Max Act: 2.6398. Min Act: -0.0000

Data Index: 1348476 (C4 (Web Text))

Max Activating Token Index: 919

Text #18

Max Range: 4.0953. Min Range: -4.0953

Max Act: 2.6335. Min Act: -0.0000

Data Index: 1320783 (C4 (Web Text))

Max Activating Token Index: 299

Text #19

Max Range: 4.0953. Min Range: -4.0953

Max Act: 2.4929. Min Act: -0.0000

Data Index: 194558 (C4 (Web Text))

Max Activating Token Index: 820