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

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

Neuron 1270 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3005. Min Range: -1.3005

Max Act: 1.2937. Min Act: -0.0001

Data Index: 17505 (C4 (Web Text))

Max Activating Token Index: 829

Text #1

Max Range: 1.3005. Min Range: -1.3005

Max Act: 1.3005. Min Act: -0.0002

Data Index: 270259 (C4 (Web Text))

Max Activating Token Index: 375

Text #2

Max Range: 1.3005. Min Range: -1.3005

Max Act: 1.2315. Min Act: -0.0002

Data Index: 1210874 (C4 (Web Text))

Max Activating Token Index: 672

Text #3

Max Range: 1.3005. Min Range: -1.3005

Max Act: 1.1390. Min Act: -0.0002

Data Index: 1035984 (C4 (Web Text))

Max Activating Token Index: 881

Text #4

Max Range: 1.3005. Min Range: -1.3005

Max Act: 1.2001. Min Act: -0.0001

Data Index: 852897 (C4 (Web Text))

Max Activating Token Index: 572

Text #5

Max Range: 1.3005. Min Range: -1.3005

Max Act: 1.2140. Min Act: -0.0002

Data Index: 1306296 (C4 (Web Text))

Max Activating Token Index: 24

Text #6

Max Range: 1.3005. Min Range: -1.3005

Max Act: 1.2113. Min Act: -0.0002

Data Index: 546604 (C4 (Web Text))

Max Activating Token Index: 696

Text #7

Max Range: 1.3005. Min Range: -1.3005

Max Act: 1.1485. Min Act: -0.0002

Data Index: 1196673 (C4 (Web Text))

Max Activating Token Index: 648

Text #8

Max Range: 1.3005. Min Range: -1.3005

Max Act: 1.2420. Min Act: -0.0001

Data Index: 1007094 (C4 (Web Text))

Max Activating Token Index: 686

Text #9

Max Range: 1.3005. Min Range: -1.3005

Max Act: 1.1158. Min Act: -0.0002

Data Index: 554694 (C4 (Web Text))

Max Activating Token Index: 856

Text #10

Max Range: 1.3005. Min Range: -1.3005

Max Act: 1.1734. Min Act: -0.0002

Data Index: 240416 (C4 (Web Text))

Max Activating Token Index: 963

Text #11

Max Range: 1.3005. Min Range: -1.3005

Max Act: 1.1511. Min Act: -0.0002

Data Index: 318440 (C4 (Web Text))

Max Activating Token Index: 788

Text #12

Max Range: 1.3005. Min Range: -1.3005

Max Act: 1.1869. Min Act: -0.0002

Data Index: 316752 (C4 (Web Text))

Max Activating Token Index: 836

Text #13

Max Range: 1.3005. Min Range: -1.3005

Max Act: 1.1778. Min Act: -0.0002

Data Index: 359610 (C4 (Web Text))

Max Activating Token Index: 429

Text #14

Max Range: 1.3005. Min Range: -1.3005

Max Act: 1.1387. Min Act: -0.0002

Data Index: 1241630 (C4 (Web Text))

Max Activating Token Index: 673

Text #15

Max Range: 1.3005. Min Range: -1.3005

Max Act: 1.1020. Min Act: -0.0001

Data Index: 539305 (C4 (Web Text))

Max Activating Token Index: 624

Text #16

Max Range: 1.3005. Min Range: -1.3005

Max Act: 1.1016. Min Act: -0.0002

Data Index: 259830 (C4 (Web Text))

Max Activating Token Index: 630

Text #17

Max Range: 1.3005. Min Range: -1.3005

Max Act: 1.1410. Min Act: -0.0002

Data Index: 281257 (C4 (Web Text))

Max Activating Token Index: 771

Text #18

Max Range: 1.3005. Min Range: -1.3005

Max Act: 1.1458. Min Act: -0.0001

Data Index: 868440 (C4 (Web Text))

Max Activating Token Index: 702

Text #19

Max Range: 1.3005. Min Range: -1.3005

Max Act: 1.1822. Min Act: -0.0001

Data Index: 701793 (C4 (Web Text))

Max Activating Token Index: 776