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

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

Neuron 5097 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: 0.2935. Min Range: -0.2935

Max Act: 0.2935. Min Act: -0.0000

Data Index: 588067 (C4 (Web Text))

Max Activating Token Index: 913

Text #1

Max Range: 0.2935. Min Range: -0.2935

Max Act: 0.2598. Min Act: -0.0000

Data Index: 367526 (C4 (Web Text))

Max Activating Token Index: 842

Text #2

Max Range: 0.2935. Min Range: -0.2935

Max Act: 0.2598. Min Act: -0.0000

Data Index: 733861 (C4 (Web Text))

Max Activating Token Index: 862

Text #3

Max Range: 0.2935. Min Range: -0.2935

Max Act: 0.2251. Min Act: -0.0000

Data Index: 838746 (C4 (Web Text))

Max Activating Token Index: 323

Text #4

Max Range: 0.2935. Min Range: -0.2935

Max Act: 0.2277. Min Act: -0.0000

Data Index: 418111 (C4 (Web Text))

Max Activating Token Index: 320

Text #5

Max Range: 0.2935. Min Range: -0.2935

Max Act: 0.2207. Min Act: -0.0000

Data Index: 636822 (C4 (Web Text))

Max Activating Token Index: 372

Text #6

Max Range: 0.2935. Min Range: -0.2935

Max Act: 0.2150. Min Act: -0.0000

Data Index: 359956 (C4 (Web Text))

Max Activating Token Index: 826

Text #7

Max Range: 0.2935. Min Range: -0.2935

Max Act: 0.2098. Min Act: -0.0000

Data Index: 129205 (C4 (Web Text))

Max Activating Token Index: 926

Text #8

Max Range: 0.2935. Min Range: -0.2935

Max Act: 0.1986. Min Act: -0.0000

Data Index: 167937 (C4 (Web Text))

Max Activating Token Index: 427

Text #9

Max Range: 0.2935. Min Range: -0.2935

Max Act: 0.1981. Min Act: -0.0000

Data Index: 1188237 (C4 (Web Text))

Max Activating Token Index: 941

Text #10

Max Range: 0.2935. Min Range: -0.2935

Max Act: 0.2052. Min Act: -0.0000

Data Index: 566549 (C4 (Web Text))

Max Activating Token Index: 278

Text #11

Max Range: 0.2935. Min Range: -0.2935

Max Act: 0.2003. Min Act: -0.0000

Data Index: 700188 (C4 (Web Text))

Max Activating Token Index: 405

Text #12

Max Range: 0.2935. Min Range: -0.2935

Max Act: 0.1939. Min Act: -0.0000

Data Index: 744476 (C4 (Web Text))

Max Activating Token Index: 557

Text #13

Max Range: 0.2935. Min Range: -0.2935

Max Act: 0.1915. Min Act: -0.0000

Data Index: 352114 (C4 (Web Text))

Max Activating Token Index: 380

Text #14

Max Range: 0.2935. Min Range: -0.2935

Max Act: 0.1839. Min Act: -0.0000

Data Index: 783962 (C4 (Web Text))

Max Activating Token Index: 400

Text #15

Max Range: 0.2935. Min Range: -0.2935

Max Act: 0.1887. Min Act: -0.0000

Data Index: 185783 (C4 (Web Text))

Max Activating Token Index: 384

Text #16

Max Range: 0.2935. Min Range: -0.2935

Max Act: 0.2077. Min Act: -0.0000

Data Index: 749797 (C4 (Web Text))

Max Activating Token Index: 462

Text #17

Max Range: 0.2935. Min Range: -0.2935

Max Act: 0.1861. Min Act: -0.0000

Data Index: 210384 (C4 (Web Text))

Max Activating Token Index: 571

Text #18

Max Range: 0.2935. Min Range: -0.2935

Max Act: 0.1751. Min Act: -0.0000

Data Index: 622095 (C4 (Web Text))

Max Activating Token Index: 624

Text #19

Max Range: 0.2935. Min Range: -0.2935

Max Act: 0.1817. Min Act: -0.0000

Data Index: 382463 (C4 (Web Text))

Max Activating Token Index: 454