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

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

Neuron 3704 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: 1.5172. Min Range: -1.5172

Max Act: 1.5172. Min Act: -0.0000

Data Index: 891321 (C4 (Web Text))

Max Activating Token Index: 801

Text #1

Max Range: 1.5172. Min Range: -1.5172

Max Act: 1.2601. Min Act: -0.0000

Data Index: 156868 (C4 (Web Text))

Max Activating Token Index: 299

Text #2

Max Range: 1.5172. Min Range: -1.5172

Max Act: 1.2633. Min Act: -0.0000

Data Index: 167596 (C4 (Web Text))

Max Activating Token Index: 777

Text #3

Max Range: 1.5172. Min Range: -1.5172

Max Act: 1.2844. Min Act: -0.0001

Data Index: 941479 (C4 (Web Text))

Max Activating Token Index: 346

Text #4

Max Range: 1.5172. Min Range: -1.5172

Max Act: 1.1862. Min Act: -0.0001

Data Index: 758367 (C4 (Web Text))

Max Activating Token Index: 885

Text #5

Max Range: 1.5172. Min Range: -1.5172

Max Act: 1.1987. Min Act: -0.0000

Data Index: 891990 (C4 (Web Text))

Max Activating Token Index: 871

Text #6

Max Range: 1.5172. Min Range: -1.5172

Max Act: 1.1983. Min Act: -0.0001

Data Index: 844207 (C4 (Web Text))

Max Activating Token Index: 829

Text #7

Max Range: 1.5172. Min Range: -1.5172

Max Act: 1.1723. Min Act: -0.0001

Data Index: 738538 (C4 (Web Text))

Max Activating Token Index: 709

Text #8

Max Range: 1.5172. Min Range: -1.5172

Max Act: 1.0968. Min Act: -0.0001

Data Index: 472395 (C4 (Web Text))

Max Activating Token Index: 590

Text #9

Max Range: 1.5172. Min Range: -1.5172

Max Act: 1.1022. Min Act: -0.0000

Data Index: 477448 (C4 (Web Text))

Max Activating Token Index: 891

Text #10

Max Range: 1.5172. Min Range: -1.5172

Max Act: 1.0422. Min Act: -0.0001

Data Index: 469416 (C4 (Web Text))

Max Activating Token Index: 922

Text #11

Max Range: 1.5172. Min Range: -1.5172

Max Act: 1.1843. Min Act: -0.0000

Data Index: 89043 (C4 (Web Text))

Max Activating Token Index: 138

Text #12

Max Range: 1.5172. Min Range: -1.5172

Max Act: 1.0443. Min Act: -0.0000

Data Index: 311828 (C4 (Web Text))

Max Activating Token Index: 759

Text #13

Max Range: 1.5172. Min Range: -1.5172

Max Act: 1.0975. Min Act: -0.0000

Data Index: 1010124 (C4 (Web Text))

Max Activating Token Index: 94

Text #14

Max Range: 1.5172. Min Range: -1.5172

Max Act: 0.9422. Min Act: -0.0001

Data Index: 1006651 (C4 (Web Text))

Max Activating Token Index: 566

Text #15

Max Range: 1.5172. Min Range: -1.5172

Max Act: 1.0239. Min Act: -0.0001

Data Index: 315297 (C4 (Web Text))

Max Activating Token Index: 862

Text #16

Max Range: 1.5172. Min Range: -1.5172

Max Act: 0.9980. Min Act: -0.0001

Data Index: 83240 (C4 (Web Text))

Max Activating Token Index: 696

Text #17

Max Range: 1.5172. Min Range: -1.5172

Max Act: 0.9867. Min Act: -0.0000

Data Index: 944084 (C4 (Web Text))

Max Activating Token Index: 99

Text #18

Max Range: 1.5172. Min Range: -1.5172

Max Act: 1.0410. Min Act: -0.0000

Data Index: 520347 (C4 (Web Text))

Max Activating Token Index: 528

Text #19

Max Range: 1.5172. Min Range: -1.5172

Max Act: 0.9824. Min Act: -0.0000

Data Index: 844951 (C4 (Web Text))

Max Activating Token Index: 668