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

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

Neuron 1611 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2483. Min Range: -0.2483

Max Act: 0.2483. Min Act: -0.0001

Data Index: 1291518 (C4 (Web Text))

Max Activating Token Index: 929

Text #1

Max Range: 0.2483. Min Range: -0.2483

Max Act: 0.2280. Min Act: -0.0001

Data Index: 1092706 (C4 (Web Text))

Max Activating Token Index: 757

Text #2

Max Range: 0.2483. Min Range: -0.2483

Max Act: 0.2180. Min Act: -0.0001

Data Index: 375266 (C4 (Web Text))

Max Activating Token Index: 759

Text #3

Max Range: 0.2483. Min Range: -0.2483

Max Act: 0.1994. Min Act: -0.0001

Data Index: 352878 (C4 (Web Text))

Max Activating Token Index: 684

Text #4

Max Range: 0.2483. Min Range: -0.2483

Max Act: 0.2264. Min Act: -0.0001

Data Index: 1178628 (C4 (Web Text))

Max Activating Token Index: 177

Text #5

Max Range: 0.2483. Min Range: -0.2483

Max Act: 0.2145. Min Act: -0.0001

Data Index: 1060429 (C4 (Web Text))

Max Activating Token Index: 448

Text #6

Max Range: 0.2483. Min Range: -0.2483

Max Act: 0.2071. Min Act: -0.0001

Data Index: 120069 (C4 (Web Text))

Max Activating Token Index: 332

Text #7

Max Range: 0.2483. Min Range: -0.2483

Max Act: 0.2118. Min Act: -0.0001

Data Index: 1450268 (Python Code)

Max Activating Token Index: 903

Text #8

Max Range: 0.2483. Min Range: -0.2483

Max Act: 0.1969. Min Act: -0.0001

Data Index: 693131 (C4 (Web Text))

Max Activating Token Index: 850

Text #9

Max Range: 0.2483. Min Range: -0.2483

Max Act: 0.1916. Min Act: -0.0001

Data Index: 241543 (C4 (Web Text))

Max Activating Token Index: 648

Text #10

Max Range: 0.2483. Min Range: -0.2483

Max Act: 0.1851. Min Act: -0.0001

Data Index: 801618 (C4 (Web Text))

Max Activating Token Index: 677

Text #11

Max Range: 0.2483. Min Range: -0.2483

Max Act: 0.1977. Min Act: -0.0001

Data Index: 1186130 (C4 (Web Text))

Max Activating Token Index: 910

Text #12

Max Range: 0.2483. Min Range: -0.2483

Max Act: 0.1820. Min Act: -0.0001

Data Index: 436352 (C4 (Web Text))

Max Activating Token Index: 829

Text #13

Max Range: 0.2483. Min Range: -0.2483

Max Act: 0.1980. Min Act: -0.0001

Data Index: 141804 (C4 (Web Text))

Max Activating Token Index: 506

Text #14

Max Range: 0.2483. Min Range: -0.2483

Max Act: 0.1903. Min Act: -0.0001

Data Index: 545461 (C4 (Web Text))

Max Activating Token Index: 988

Text #15

Max Range: 0.2483. Min Range: -0.2483

Max Act: 0.1948. Min Act: -0.0001

Data Index: 106040 (C4 (Web Text))

Max Activating Token Index: 699

Text #16

Max Range: 0.2483. Min Range: -0.2483

Max Act: 0.1839. Min Act: -0.0001

Data Index: 256036 (C4 (Web Text))

Max Activating Token Index: 38

Text #17

Max Range: 0.2483. Min Range: -0.2483

Max Act: 0.1846. Min Act: -0.0001

Data Index: 752942 (C4 (Web Text))

Max Activating Token Index: 5

Text #18

Max Range: 0.2483. Min Range: -0.2483

Max Act: 0.1828. Min Act: -0.0001

Data Index: 270923 (C4 (Web Text))

Max Activating Token Index: 945

Text #19

Max Range: 0.2483. Min Range: -0.2483

Max Act: 0.1701. Min Act: -0.0001

Data Index: 943234 (C4 (Web Text))

Max Activating Token Index: 625