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

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

Neuron 593 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6349. Min Range: -2.6349

Max Act: 2.6349. Min Act: -0.0000

Data Index: 1007931 (C4 (Web Text))

Max Activating Token Index: 713

Text #1

Max Range: 2.6349. Min Range: -2.6349

Max Act: 2.1116. Min Act: -0.0000

Data Index: 1373477 (Python Code)

Max Activating Token Index: 681

Text #2

Max Range: 2.6349. Min Range: -2.6349

Max Act: 2.2299. Min Act: -0.0000

Data Index: 5527 (C4 (Web Text))

Max Activating Token Index: 468

Text #3

Max Range: 2.6349. Min Range: -2.6349

Max Act: 2.0258. Min Act: -0.0000

Data Index: 1274200 (C4 (Web Text))

Max Activating Token Index: 434

Text #4

Max Range: 2.6349. Min Range: -2.6349

Max Act: 1.9974. Min Act: -0.0000

Data Index: 1254399 (C4 (Web Text))

Max Activating Token Index: 105

Text #5

Max Range: 2.6349. Min Range: -2.6349

Max Act: 1.9884. Min Act: 0.0000

Data Index: 1308242 (C4 (Web Text))

Max Activating Token Index: 124

Text #6

Max Range: 2.6349. Min Range: -2.6349

Max Act: 1.8936. Min Act: -0.0000

Data Index: 1183000 (C4 (Web Text))

Max Activating Token Index: 811

Text #7

Max Range: 2.6349. Min Range: -2.6349

Max Act: 1.8635. Min Act: -0.0000

Data Index: 932471 (C4 (Web Text))

Max Activating Token Index: 619

Text #8

Max Range: 2.6349. Min Range: -2.6349

Max Act: 1.6723. Min Act: 0.0000

Data Index: 932268 (C4 (Web Text))

Max Activating Token Index: 57

Text #9

Max Range: 2.6349. Min Range: -2.6349

Max Act: 1.6844. Min Act: -0.0000

Data Index: 524431 (C4 (Web Text))

Max Activating Token Index: 1013

Text #10

Max Range: 2.6349. Min Range: -2.6349

Max Act: 1.7552. Min Act: -0.0000

Data Index: 655560 (C4 (Web Text))

Max Activating Token Index: 821

Text #11

Max Range: 2.6349. Min Range: -2.6349

Max Act: 1.6423. Min Act: -0.0000

Data Index: 198155 (C4 (Web Text))

Max Activating Token Index: 814

Text #12

Max Range: 2.6349. Min Range: -2.6349

Max Act: 1.6337. Min Act: -0.0000

Data Index: 890230 (C4 (Web Text))

Max Activating Token Index: 632

Text #13

Max Range: 2.6349. Min Range: -2.6349

Max Act: 1.6016. Min Act: -0.0000

Data Index: 1058363 (C4 (Web Text))

Max Activating Token Index: 322

Text #14

Max Range: 2.6349. Min Range: -2.6349

Max Act: 1.5734. Min Act: -0.0000

Data Index: 1593025 (Python Code)

Max Activating Token Index: 305

Text #15

Max Range: 2.6349. Min Range: -2.6349

Max Act: 1.4836. Min Act: -0.0000

Data Index: 647793 (C4 (Web Text))

Max Activating Token Index: 900

Text #16

Max Range: 2.6349. Min Range: -2.6349

Max Act: 1.5544. Min Act: -0.0000

Data Index: 63160 (C4 (Web Text))

Max Activating Token Index: 206

Text #17

Max Range: 2.6349. Min Range: -2.6349

Max Act: 1.5466. Min Act: -0.0000

Data Index: 915313 (C4 (Web Text))

Max Activating Token Index: 420

Text #18

Max Range: 2.6349. Min Range: -2.6349

Max Act: 1.4524. Min Act: -0.0000

Data Index: 300745 (C4 (Web Text))

Max Activating Token Index: 846

Text #19

Max Range: 2.6349. Min Range: -2.6349

Max Act: 1.5308. Min Act: -0.0000

Data Index: 556418 (C4 (Web Text))

Max Activating Token Index: 244