Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 586 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0501. Min Act: -0.0004

Data Index: 143568 (C4 (Web Text))

Max Activating Token Index: 17

Text #1

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0477. Min Act: -0.0004

Data Index: 603044 (C4 (Web Text))

Max Activating Token Index: 164

Text #2

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0469. Min Act: -0.0004

Data Index: 1149424 (C4 (Web Text))

Max Activating Token Index: 491

Text #3

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0474. Min Act: -0.0004

Data Index: 1047024 (C4 (Web Text))

Max Activating Token Index: 866

Text #4

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0423. Min Act: -0.0004

Data Index: 227244 (C4 (Web Text))

Max Activating Token Index: 357

Text #5

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0432. Min Act: -0.0004

Data Index: 420114 (C4 (Web Text))

Max Activating Token Index: 848

Text #6

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0441. Min Act: -0.0004

Data Index: 149973 (C4 (Web Text))

Max Activating Token Index: 175

Text #7

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0462. Min Act: -0.0004

Data Index: 11800 (C4 (Web Text))

Max Activating Token Index: 8

Text #8

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0419. Min Act: -0.0004

Data Index: 548116 (C4 (Web Text))

Max Activating Token Index: 875

Text #9

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0448. Min Act: -0.0004

Data Index: 123502 (C4 (Web Text))

Max Activating Token Index: 501

Text #10

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0464. Min Act: -0.0004

Data Index: 112947 (C4 (Web Text))

Max Activating Token Index: 951

Text #11

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0408. Min Act: -0.0004

Data Index: 1141118 (C4 (Web Text))

Max Activating Token Index: 890

Text #12

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0413. Min Act: -0.0004

Data Index: 535672 (C4 (Web Text))

Max Activating Token Index: 273

Text #13

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0434. Min Act: -0.0004

Data Index: 1162893 (C4 (Web Text))

Max Activating Token Index: 355

Text #14

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0421. Min Act: -0.0004

Data Index: 786641 (C4 (Web Text))

Max Activating Token Index: 950

Text #15

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0445. Min Act: -0.0004

Data Index: 650996 (C4 (Web Text))

Max Activating Token Index: 315

Text #16

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0456. Min Act: -0.0004

Data Index: 813580 (C4 (Web Text))

Max Activating Token Index: 383

Text #17

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0442. Min Act: -0.0004

Data Index: 499454 (C4 (Web Text))

Max Activating Token Index: 79

Text #18

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0431. Min Act: -0.0004

Data Index: 873011 (C4 (Web Text))

Max Activating Token Index: 797

Text #19

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0437. Min Act: -0.0004

Data Index: 751420 (C4 (Web Text))

Max Activating Token Index: 90