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

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

Neuron 440 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3045. Min Range: -0.3045

Max Act: 0.3045. Min Act: -0.0000

Data Index: 432296 (C4 (Web Text))

Max Activating Token Index: 29

Text #1

Max Range: 0.3045. Min Range: -0.3045

Max Act: 0.2835. Min Act: -0.0001

Data Index: 538634 (C4 (Web Text))

Max Activating Token Index: 194

Text #2

Max Range: 0.3045. Min Range: -0.3045

Max Act: 0.2491. Min Act: -0.0001

Data Index: 458525 (C4 (Web Text))

Max Activating Token Index: 108

Text #3

Max Range: 0.3045. Min Range: -0.3045

Max Act: 0.2662. Min Act: -0.0000

Data Index: 386609 (C4 (Web Text))

Max Activating Token Index: 868

Text #4

Max Range: 0.3045. Min Range: -0.3045

Max Act: 0.2918. Min Act: -0.0001

Data Index: 486650 (C4 (Web Text))

Max Activating Token Index: 82

Text #5

Max Range: 0.3045. Min Range: -0.3045

Max Act: 0.2745. Min Act: -0.0000

Data Index: 971075 (C4 (Web Text))

Max Activating Token Index: 1000

Text #6

Max Range: 0.3045. Min Range: -0.3045

Max Act: 0.2736. Min Act: -0.0000

Data Index: 1180401 (C4 (Web Text))

Max Activating Token Index: 906

Text #7

Max Range: 0.3045. Min Range: -0.3045

Max Act: 0.2705. Min Act: -0.0001

Data Index: 1154383 (C4 (Web Text))

Max Activating Token Index: 99

Text #8

Max Range: 0.3045. Min Range: -0.3045

Max Act: 0.2790. Min Act: -0.0000

Data Index: 1159277 (C4 (Web Text))

Max Activating Token Index: 309

Text #9

Max Range: 0.3045. Min Range: -0.3045

Max Act: 0.2650. Min Act: -0.0001

Data Index: 239919 (C4 (Web Text))

Max Activating Token Index: 58

Text #10

Max Range: 0.3045. Min Range: -0.3045

Max Act: 0.2726. Min Act: -0.0001

Data Index: 1227726 (C4 (Web Text))

Max Activating Token Index: 99

Text #11

Max Range: 0.3045. Min Range: -0.3045

Max Act: 0.2587. Min Act: -0.0001

Data Index: 968908 (C4 (Web Text))

Max Activating Token Index: 730

Text #12

Max Range: 0.3045. Min Range: -0.3045

Max Act: 0.2507. Min Act: -0.0000

Data Index: 339239 (C4 (Web Text))

Max Activating Token Index: 335

Text #13

Max Range: 0.3045. Min Range: -0.3045

Max Act: 0.2495. Min Act: -0.0000

Data Index: 793422 (C4 (Web Text))

Max Activating Token Index: 414

Text #14

Max Range: 0.3045. Min Range: -0.3045

Max Act: 0.2565. Min Act: -0.0001

Data Index: 1331062 (C4 (Web Text))

Max Activating Token Index: 782

Text #15

Max Range: 0.3045. Min Range: -0.3045

Max Act: 0.2604. Min Act: -0.0000

Data Index: 1355617 (C4 (Web Text))

Max Activating Token Index: 639

Text #16

Max Range: 0.3045. Min Range: -0.3045

Max Act: 0.2410. Min Act: -0.0001

Data Index: 550537 (C4 (Web Text))

Max Activating Token Index: 659

Text #17

Max Range: 0.3045. Min Range: -0.3045

Max Act: 0.2702. Min Act: -0.0001

Data Index: 374538 (C4 (Web Text))

Max Activating Token Index: 71

Text #18

Max Range: 0.3045. Min Range: -0.3045

Max Act: 0.2505. Min Act: -0.0000

Data Index: 928631 (C4 (Web Text))

Max Activating Token Index: 125

Text #19

Max Range: 0.3045. Min Range: -0.3045

Max Act: 0.2189. Min Act: -0.0001

Data Index: 650875 (C4 (Web Text))

Max Activating Token Index: 935