Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1356 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.2598. Min Range: -1.2598

Max Act: 1.2598. Min Act: -0.0001

Data Index: 127703 (C4 (Web Text))

Max Activating Token Index: 85

Text #1

Max Range: 1.2598. Min Range: -1.2598

Max Act: 0.7308. Min Act: -0.0001

Data Index: 143359 (C4 (Web Text))

Max Activating Token Index: 112

Text #2

Max Range: 1.2598. Min Range: -1.2598

Max Act: 0.7654. Min Act: -0.0001

Data Index: 630848 (C4 (Web Text))

Max Activating Token Index: 1007

Text #3

Max Range: 1.2598. Min Range: -1.2598

Max Act: 0.6556. Min Act: -0.0001

Data Index: 248876 (C4 (Web Text))

Max Activating Token Index: 504

Text #4

Max Range: 1.2598. Min Range: -1.2598

Max Act: 0.6250. Min Act: -0.0001

Data Index: 239061 (C4 (Web Text))

Max Activating Token Index: 828

Text #5

Max Range: 1.2598. Min Range: -1.2598

Max Act: 0.6342. Min Act: -0.0000

Data Index: 896910 (C4 (Web Text))

Max Activating Token Index: 220

Text #6

Max Range: 1.2598. Min Range: -1.2598

Max Act: 0.6195. Min Act: -0.0001

Data Index: 1592348 (Python Code)

Max Activating Token Index: 932

Text #7

Max Range: 1.2598. Min Range: -1.2598

Max Act: 0.6430. Min Act: -0.0001

Data Index: 891296 (C4 (Web Text))

Max Activating Token Index: 633

Text #8

Max Range: 1.2598. Min Range: -1.2598

Max Act: 0.6229. Min Act: -0.0001

Data Index: 751335 (C4 (Web Text))

Max Activating Token Index: 388

Text #9

Max Range: 1.2598. Min Range: -1.2598

Max Act: 0.5972. Min Act: -0.0001

Data Index: 1022559 (C4 (Web Text))

Max Activating Token Index: 642

Text #10

Max Range: 1.2598. Min Range: -1.2598

Max Act: 0.5247. Min Act: -0.0001

Data Index: 1180291 (C4 (Web Text))

Max Activating Token Index: 748

Text #11

Max Range: 1.2598. Min Range: -1.2598

Max Act: 0.5711. Min Act: -0.0001

Data Index: 958121 (C4 (Web Text))

Max Activating Token Index: 40

Text #12

Max Range: 1.2598. Min Range: -1.2598

Max Act: 0.6234. Min Act: -0.0001

Data Index: 895134 (C4 (Web Text))

Max Activating Token Index: 786

Text #13

Max Range: 1.2598. Min Range: -1.2598

Max Act: 0.5800. Min Act: -0.0001

Data Index: 303481 (C4 (Web Text))

Max Activating Token Index: 740

Text #14

Max Range: 1.2598. Min Range: -1.2598

Max Act: 0.5837. Min Act: -0.0000

Data Index: 1425236 (Python Code)

Max Activating Token Index: 680

Text #15

Max Range: 1.2598. Min Range: -1.2598

Max Act: 0.6303. Min Act: -0.0000

Data Index: 1415989 (Python Code)

Max Activating Token Index: 878

Text #16

Max Range: 1.2598. Min Range: -1.2598

Max Act: 0.6107. Min Act: -0.0000

Data Index: 349964 (C4 (Web Text))

Max Activating Token Index: 176

Text #17

Max Range: 1.2598. Min Range: -1.2598

Max Act: 0.6077. Min Act: -0.0001

Data Index: 901795 (C4 (Web Text))

Max Activating Token Index: 133

Text #18

Max Range: 1.2598. Min Range: -1.2598

Max Act: 0.5875. Min Act: -0.0001

Data Index: 460466 (C4 (Web Text))

Max Activating Token Index: 690

Text #19

Max Range: 1.2598. Min Range: -1.2598

Max Act: 0.6006. Min Act: -0.0000

Data Index: 1623109 (Python Code)

Max Activating Token Index: 785