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

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

Neuron 4900 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1932. Min Range: -2.1932

Max Act: 2.1932. Min Act: -0.0000

Data Index: 524766 (C4 (Web Text))

Max Activating Token Index: 542

Text #1

Max Range: 2.1932. Min Range: -2.1932

Max Act: 1.8410. Min Act: -0.0000

Data Index: 207671 (C4 (Web Text))

Max Activating Token Index: 388

Text #2

Max Range: 2.1932. Min Range: -2.1932

Max Act: 1.4917. Min Act: -0.0000

Data Index: 391431 (C4 (Web Text))

Max Activating Token Index: 62

Text #3

Max Range: 2.1932. Min Range: -2.1932

Max Act: 1.4595. Min Act: -0.0000

Data Index: 672718 (C4 (Web Text))

Max Activating Token Index: 228

Text #4

Max Range: 2.1932. Min Range: -2.1932

Max Act: 1.2794. Min Act: -0.0000

Data Index: 208908 (C4 (Web Text))

Max Activating Token Index: 316

Text #5

Max Range: 2.1932. Min Range: -2.1932

Max Act: 1.2941. Min Act: -0.0000

Data Index: 305074 (C4 (Web Text))

Max Activating Token Index: 100

Text #6

Max Range: 2.1932. Min Range: -2.1932

Max Act: 1.3539. Min Act: -0.0000

Data Index: 326322 (C4 (Web Text))

Max Activating Token Index: 933

Text #7

Max Range: 2.1932. Min Range: -2.1932

Max Act: 1.4162. Min Act: -0.0000

Data Index: 689731 (C4 (Web Text))

Max Activating Token Index: 227

Text #8

Max Range: 2.1932. Min Range: -2.1932

Max Act: 1.2616. Min Act: -0.0000

Data Index: 1346849 (C4 (Web Text))

Max Activating Token Index: 826

Text #9

Max Range: 2.1932. Min Range: -2.1932

Max Act: 1.3242. Min Act: -0.0000

Data Index: 186315 (C4 (Web Text))

Max Activating Token Index: 560

Text #10

Max Range: 2.1932. Min Range: -2.1932

Max Act: 1.3107. Min Act: -0.0000

Data Index: 357017 (C4 (Web Text))

Max Activating Token Index: 459

Text #11

Max Range: 2.1932. Min Range: -2.1932

Max Act: 1.3004. Min Act: -0.0000

Data Index: 105319 (C4 (Web Text))

Max Activating Token Index: 727

Text #12

Max Range: 2.1932. Min Range: -2.1932

Max Act: 1.3392. Min Act: -0.0000

Data Index: 529829 (C4 (Web Text))

Max Activating Token Index: 329

Text #13

Max Range: 2.1932. Min Range: -2.1932

Max Act: 1.1580. Min Act: -0.0000

Data Index: 675130 (C4 (Web Text))

Max Activating Token Index: 297

Text #14

Max Range: 2.1932. Min Range: -2.1932

Max Act: 1.2296. Min Act: -0.0000

Data Index: 718653 (C4 (Web Text))

Max Activating Token Index: 218

Text #15

Max Range: 2.1932. Min Range: -2.1932

Max Act: 1.1516. Min Act: -0.0000

Data Index: 1267597 (C4 (Web Text))

Max Activating Token Index: 125

Text #16

Max Range: 2.1932. Min Range: -2.1932

Max Act: 1.1806. Min Act: -0.0000

Data Index: 491047 (C4 (Web Text))

Max Activating Token Index: 717

Text #17

Max Range: 2.1932. Min Range: -2.1932

Max Act: 1.0846. Min Act: -0.0000

Data Index: 641041 (C4 (Web Text))

Max Activating Token Index: 868

Text #18

Max Range: 2.1932. Min Range: -2.1932

Max Act: 1.1393. Min Act: -0.0000

Data Index: 591685 (C4 (Web Text))

Max Activating Token Index: 89

Text #19

Max Range: 2.1932. Min Range: -2.1932

Max Act: 1.1394. Min Act: -0.0000

Data Index: 1075655 (C4 (Web Text))

Max Activating Token Index: 503