Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3864 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2276. Min Range: -0.2276

Max Act: 0.2276. Min Act: -0.0001

Data Index: 426959 (C4 (Web Text))

Max Activating Token Index: 459

Text #1

Max Range: 0.2276. Min Range: -0.2276

Max Act: 0.1884. Min Act: -0.0001

Data Index: 29676 (C4 (Web Text))

Max Activating Token Index: 136

Text #2

Max Range: 0.2276. Min Range: -0.2276

Max Act: 0.1834. Min Act: -0.0001

Data Index: 90702 (C4 (Web Text))

Max Activating Token Index: 163

Text #3

Max Range: 0.2276. Min Range: -0.2276

Max Act: 0.1907. Min Act: -0.0001

Data Index: 1125052 (C4 (Web Text))

Max Activating Token Index: 880

Text #4

Max Range: 0.2276. Min Range: -0.2276

Max Act: 0.1763. Min Act: -0.0001

Data Index: 27347 (C4 (Web Text))

Max Activating Token Index: 429

Text #5

Max Range: 0.2276. Min Range: -0.2276

Max Act: 0.1753. Min Act: -0.0001

Data Index: 1247115 (C4 (Web Text))

Max Activating Token Index: 298

Text #6

Max Range: 0.2276. Min Range: -0.2276

Max Act: 0.1739. Min Act: -0.0001

Data Index: 538461 (C4 (Web Text))

Max Activating Token Index: 977

Text #7

Max Range: 0.2276. Min Range: -0.2276

Max Act: 0.1728. Min Act: -0.0001

Data Index: 520795 (C4 (Web Text))

Max Activating Token Index: 620

Text #8

Max Range: 0.2276. Min Range: -0.2276

Max Act: 0.1643. Min Act: -0.0001

Data Index: 1257292 (C4 (Web Text))

Max Activating Token Index: 805

Text #9

Max Range: 0.2276. Min Range: -0.2276

Max Act: 0.1556. Min Act: -0.0001

Data Index: 362004 (C4 (Web Text))

Max Activating Token Index: 476

Text #10

Max Range: 0.2276. Min Range: -0.2276

Max Act: 0.1467. Min Act: -0.0001

Data Index: 1080254 (C4 (Web Text))

Max Activating Token Index: 471

Text #11

Max Range: 0.2276. Min Range: -0.2276

Max Act: 0.1469. Min Act: -0.0001

Data Index: 250188 (C4 (Web Text))

Max Activating Token Index: 439

Text #12

Max Range: 0.2276. Min Range: -0.2276

Max Act: 0.1588. Min Act: -0.0000

Data Index: 899845 (C4 (Web Text))

Max Activating Token Index: 87

Text #13

Max Range: 0.2276. Min Range: -0.2276

Max Act: 0.1575. Min Act: -0.0001

Data Index: 364686 (C4 (Web Text))

Max Activating Token Index: 101

Text #14

Max Range: 0.2276. Min Range: -0.2276

Max Act: 0.1520. Min Act: -0.0001

Data Index: 24244 (C4 (Web Text))

Max Activating Token Index: 329

Text #15

Max Range: 0.2276. Min Range: -0.2276

Max Act: 0.1323. Min Act: -0.0001

Data Index: 119939 (C4 (Web Text))

Max Activating Token Index: 846

Text #16

Max Range: 0.2276. Min Range: -0.2276

Max Act: 0.1484. Min Act: -0.0001

Data Index: 1452441 (Python Code)

Max Activating Token Index: 840

Text #17

Max Range: 0.2276. Min Range: -0.2276

Max Act: 0.1429. Min Act: -0.0000

Data Index: 646645 (C4 (Web Text))

Max Activating Token Index: 195

Text #18

Max Range: 0.2276. Min Range: -0.2276

Max Act: 0.1533. Min Act: -0.0001

Data Index: 733841 (C4 (Web Text))

Max Activating Token Index: 115

Text #19

Max Range: 0.2276. Min Range: -0.2276

Max Act: 0.1322. Min Act: -0.0000

Data Index: 1265114 (C4 (Web Text))

Max Activating Token Index: 1004