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

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

Neuron 1059 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3173. Min Range: -0.3173

Max Act: 0.3026. Min Act: -0.0000

Data Index: 980819 (C4 (Web Text))

Max Activating Token Index: 160

Text #1

Max Range: 0.3173. Min Range: -0.3173

Max Act: 0.3171. Min Act: -0.0000

Data Index: 294481 (C4 (Web Text))

Max Activating Token Index: 734

Text #2

Max Range: 0.3173. Min Range: -0.3173

Max Act: 0.2930. Min Act: -0.0000

Data Index: 421138 (C4 (Web Text))

Max Activating Token Index: 481

Text #3

Max Range: 0.3173. Min Range: -0.3173

Max Act: 0.3173. Min Act: -0.0000

Data Index: 181576 (C4 (Web Text))

Max Activating Token Index: 870

Text #4

Max Range: 0.3173. Min Range: -0.3173

Max Act: 0.2533. Min Act: -0.0000

Data Index: 330264 (C4 (Web Text))

Max Activating Token Index: 233

Text #5

Max Range: 0.3173. Min Range: -0.3173

Max Act: 0.2836. Min Act: -0.0000

Data Index: 371192 (C4 (Web Text))

Max Activating Token Index: 704

Text #6

Max Range: 0.3173. Min Range: -0.3173

Max Act: 0.2468. Min Act: -0.0000

Data Index: 620745 (C4 (Web Text))

Max Activating Token Index: 586

Text #7

Max Range: 0.3173. Min Range: -0.3173

Max Act: 0.2712. Min Act: -0.0000

Data Index: 819960 (C4 (Web Text))

Max Activating Token Index: 188

Text #8

Max Range: 0.3173. Min Range: -0.3173

Max Act: 0.2460. Min Act: -0.0000

Data Index: 284648 (C4 (Web Text))

Max Activating Token Index: 971

Text #9

Max Range: 0.3173. Min Range: -0.3173

Max Act: 0.2362. Min Act: -0.0000

Data Index: 2035 (C4 (Web Text))

Max Activating Token Index: 736

Text #10

Max Range: 0.3173. Min Range: -0.3173

Max Act: 0.2475. Min Act: -0.0000

Data Index: 565024 (C4 (Web Text))

Max Activating Token Index: 203

Text #11

Max Range: 0.3173. Min Range: -0.3173

Max Act: 0.2380. Min Act: -0.0000

Data Index: 1186165 (C4 (Web Text))

Max Activating Token Index: 836

Text #12

Max Range: 0.3173. Min Range: -0.3173

Max Act: 0.2155. Min Act: -0.0000

Data Index: 313479 (C4 (Web Text))

Max Activating Token Index: 742

Text #13

Max Range: 0.3173. Min Range: -0.3173

Max Act: 0.2216. Min Act: -0.0000

Data Index: 406694 (C4 (Web Text))

Max Activating Token Index: 481

Text #14

Max Range: 0.3173. Min Range: -0.3173

Max Act: 0.2088. Min Act: -0.0000

Data Index: 708636 (C4 (Web Text))

Max Activating Token Index: 530

Text #15

Max Range: 0.3173. Min Range: -0.3173

Max Act: 0.2260. Min Act: -0.0000

Data Index: 199747 (C4 (Web Text))

Max Activating Token Index: 548

Text #16

Max Range: 0.3173. Min Range: -0.3173

Max Act: 0.2275. Min Act: -0.0000

Data Index: 146682 (C4 (Web Text))

Max Activating Token Index: 764

Text #17

Max Range: 0.3173. Min Range: -0.3173

Max Act: 0.1916. Min Act: -0.0000

Data Index: 735212 (C4 (Web Text))

Max Activating Token Index: 308

Text #18

Max Range: 0.3173. Min Range: -0.3173

Max Act: 0.2053. Min Act: -0.0000

Data Index: 478533 (C4 (Web Text))

Max Activating Token Index: 517

Text #19

Max Range: 0.3173. Min Range: -0.3173

Max Act: 0.1942. Min Act: -0.0000

Data Index: 1034255 (C4 (Web Text))

Max Activating Token Index: 717