Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3565 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.5845. Min Range: -0.5845

Max Act: 0.5559. Min Act: -0.0000

Data Index: 1131341 (C4 (Web Text))

Max Activating Token Index: 906

Text #1

Max Range: 0.5845. Min Range: -0.5845

Max Act: 0.4875. Min Act: -0.0001

Data Index: 973690 (C4 (Web Text))

Max Activating Token Index: 692

Text #2

Max Range: 0.5845. Min Range: -0.5845

Max Act: 0.5261. Min Act: -0.0001

Data Index: 230251 (C4 (Web Text))

Max Activating Token Index: 785

Text #3

Max Range: 0.5845. Min Range: -0.5845

Max Act: 0.5845. Min Act: -0.0001

Data Index: 260894 (C4 (Web Text))

Max Activating Token Index: 56

Text #4

Max Range: 0.5845. Min Range: -0.5845

Max Act: 0.5266. Min Act: -0.0001

Data Index: 434576 (C4 (Web Text))

Max Activating Token Index: 424

Text #5

Max Range: 0.5845. Min Range: -0.5845

Max Act: 0.5621. Min Act: -0.0001

Data Index: 1209334 (C4 (Web Text))

Max Activating Token Index: 938

Text #6

Max Range: 0.5845. Min Range: -0.5845

Max Act: 0.5122. Min Act: -0.0001

Data Index: 45060 (C4 (Web Text))

Max Activating Token Index: 94

Text #7

Max Range: 0.5845. Min Range: -0.5845

Max Act: 0.5390. Min Act: -0.0000

Data Index: 421135 (C4 (Web Text))

Max Activating Token Index: 9

Text #8

Max Range: 0.5845. Min Range: -0.5845

Max Act: 0.5557. Min Act: -0.0001

Data Index: 117709 (C4 (Web Text))

Max Activating Token Index: 153

Text #9

Max Range: 0.5845. Min Range: -0.5845

Max Act: 0.4925. Min Act: -0.0001

Data Index: 709367 (C4 (Web Text))

Max Activating Token Index: 1014

Text #10

Max Range: 0.5845. Min Range: -0.5845

Max Act: 0.5309. Min Act: -0.0001

Data Index: 869442 (C4 (Web Text))

Max Activating Token Index: 43

Text #11

Max Range: 0.5845. Min Range: -0.5845

Max Act: 0.5289. Min Act: -0.0000

Data Index: 523299 (C4 (Web Text))

Max Activating Token Index: 584

Text #12

Max Range: 0.5845. Min Range: -0.5845

Max Act: 0.5130. Min Act: -0.0001

Data Index: 1293078 (C4 (Web Text))

Max Activating Token Index: 403

Text #13

Max Range: 0.5845. Min Range: -0.5845

Max Act: 0.5031. Min Act: -0.0001

Data Index: 538184 (C4 (Web Text))

Max Activating Token Index: 930

Text #14

Max Range: 0.5845. Min Range: -0.5845

Max Act: 0.5034. Min Act: -0.0001

Data Index: 237863 (C4 (Web Text))

Max Activating Token Index: 548

Text #15

Max Range: 0.5845. Min Range: -0.5845

Max Act: 0.4869. Min Act: -0.0001

Data Index: 278546 (C4 (Web Text))

Max Activating Token Index: 566

Text #16

Max Range: 0.5845. Min Range: -0.5845

Max Act: 0.5020. Min Act: -0.0000

Data Index: 946236 (C4 (Web Text))

Max Activating Token Index: 495

Text #17

Max Range: 0.5845. Min Range: -0.5845

Max Act: 0.4817. Min Act: -0.0000

Data Index: 1579921 (Python Code)

Max Activating Token Index: 54

Text #18

Max Range: 0.5845. Min Range: -0.5845

Max Act: 0.5125. Min Act: -0.0001

Data Index: 821971 (C4 (Web Text))

Max Activating Token Index: 773

Text #19

Max Range: 0.5845. Min Range: -0.5845

Max Act: 0.4765. Min Act: -0.0000

Data Index: 967337 (C4 (Web Text))

Max Activating Token Index: 512