Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4533 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.5395. Min Range: -1.5395

Max Act: 1.5395. Min Act: -0.0000

Data Index: 351188 (C4 (Web Text))

Max Activating Token Index: 713

Text #1

Max Range: 1.5395. Min Range: -1.5395

Max Act: 1.0321. Min Act: -0.0000

Data Index: 772316 (C4 (Web Text))

Max Activating Token Index: 193

Text #2

Max Range: 1.5395. Min Range: -1.5395

Max Act: 1.0239. Min Act: -0.0000

Data Index: 715517 (C4 (Web Text))

Max Activating Token Index: 478

Text #3

Max Range: 1.5395. Min Range: -1.5395

Max Act: 0.9870. Min Act: -0.0000

Data Index: 1195447 (C4 (Web Text))

Max Activating Token Index: 90

Text #4

Max Range: 1.5395. Min Range: -1.5395

Max Act: 0.9759. Min Act: -0.0000

Data Index: 399469 (C4 (Web Text))

Max Activating Token Index: 556

Text #5

Max Range: 1.5395. Min Range: -1.5395

Max Act: 0.9360. Min Act: -0.0000

Data Index: 71884 (C4 (Web Text))

Max Activating Token Index: 10

Text #6

Max Range: 1.5395. Min Range: -1.5395

Max Act: 0.9178. Min Act: -0.0000

Data Index: 1236989 (C4 (Web Text))

Max Activating Token Index: 953

Text #7

Max Range: 1.5395. Min Range: -1.5395

Max Act: 0.9019. Min Act: -0.0000

Data Index: 527714 (C4 (Web Text))

Max Activating Token Index: 923

Text #8

Max Range: 1.5395. Min Range: -1.5395

Max Act: 0.9508. Min Act: -0.0000

Data Index: 195559 (C4 (Web Text))

Max Activating Token Index: 96

Text #9

Max Range: 1.5395. Min Range: -1.5395

Max Act: 0.8764. Min Act: -0.0000

Data Index: 851999 (C4 (Web Text))

Max Activating Token Index: 874

Text #10

Max Range: 1.5395. Min Range: -1.5395

Max Act: 0.8881. Min Act: -0.0000

Data Index: 987355 (C4 (Web Text))

Max Activating Token Index: 386

Text #11

Max Range: 1.5395. Min Range: -1.5395

Max Act: 0.8800. Min Act: -0.0000

Data Index: 369283 (C4 (Web Text))

Max Activating Token Index: 520

Text #12

Max Range: 1.5395. Min Range: -1.5395

Max Act: 0.8765. Min Act: -0.0000

Data Index: 85222 (C4 (Web Text))

Max Activating Token Index: 850

Text #13

Max Range: 1.5395. Min Range: -1.5395

Max Act: 0.8712. Min Act: -0.0000

Data Index: 1096818 (C4 (Web Text))

Max Activating Token Index: 647

Text #14

Max Range: 1.5395. Min Range: -1.5395

Max Act: 0.9202. Min Act: -0.0000

Data Index: 1236304 (C4 (Web Text))

Max Activating Token Index: 831

Text #15

Max Range: 1.5395. Min Range: -1.5395

Max Act: 0.8540. Min Act: -0.0000

Data Index: 650137 (C4 (Web Text))

Max Activating Token Index: 980

Text #16

Max Range: 1.5395. Min Range: -1.5395

Max Act: 0.8946. Min Act: -0.0000

Data Index: 1031006 (C4 (Web Text))

Max Activating Token Index: 808

Text #17

Max Range: 1.5395. Min Range: -1.5395

Max Act: 0.8344. Min Act: -0.0000

Data Index: 1055313 (C4 (Web Text))

Max Activating Token Index: 852

Text #18

Max Range: 1.5395. Min Range: -1.5395

Max Act: 0.7845. Min Act: -0.0000

Data Index: 1233712 (C4 (Web Text))

Max Activating Token Index: 858

Text #19

Max Range: 1.5395. Min Range: -1.5395

Max Act: 0.7697. Min Act: -0.0000

Data Index: 1230708 (C4 (Web Text))

Max Activating Token Index: 803