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

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

Neuron 6121 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: 0.5913. Min Range: -0.5913

Max Act: 0.5913. Min Act: -0.0000

Data Index: 1146371 (C4 (Web Text))

Max Activating Token Index: 466

Text #1

Max Range: 0.5913. Min Range: -0.5913

Max Act: 0.5785. Min Act: -0.0000

Data Index: 192683 (C4 (Web Text))

Max Activating Token Index: 332

Text #2

Max Range: 0.5913. Min Range: -0.5913

Max Act: 0.5464. Min Act: -0.0001

Data Index: 842625 (C4 (Web Text))

Max Activating Token Index: 865

Text #3

Max Range: 0.5913. Min Range: -0.5913

Max Act: 0.5658. Min Act: -0.0000

Data Index: 435803 (C4 (Web Text))

Max Activating Token Index: 351

Text #4

Max Range: 0.5913. Min Range: -0.5913

Max Act: 0.4290. Min Act: -0.0001

Data Index: 82333 (C4 (Web Text))

Max Activating Token Index: 302

Text #5

Max Range: 0.5913. Min Range: -0.5913

Max Act: 0.4024. Min Act: -0.0001

Data Index: 1015132 (C4 (Web Text))

Max Activating Token Index: 193

Text #6

Max Range: 0.5913. Min Range: -0.5913

Max Act: 0.3742. Min Act: -0.0000

Data Index: 667419 (C4 (Web Text))

Max Activating Token Index: 223

Text #7

Max Range: 0.5913. Min Range: -0.5913

Max Act: 0.3720. Min Act: -0.0000

Data Index: 1147731 (C4 (Web Text))

Max Activating Token Index: 581

Text #8

Max Range: 0.5913. Min Range: -0.5913

Max Act: 0.2749. Min Act: -0.0001

Data Index: 559078 (C4 (Web Text))

Max Activating Token Index: 906

Text #9

Max Range: 0.5913. Min Range: -0.5913

Max Act: 0.2788. Min Act: -0.0001

Data Index: 836783 (C4 (Web Text))

Max Activating Token Index: 599

Text #10

Max Range: 0.5913. Min Range: -0.5913

Max Act: 0.2953. Min Act: -0.0001

Data Index: 992979 (C4 (Web Text))

Max Activating Token Index: 820

Text #11

Max Range: 0.5913. Min Range: -0.5913

Max Act: 0.3231. Min Act: -0.0001

Data Index: 264892 (C4 (Web Text))

Max Activating Token Index: 238

Text #12

Max Range: 0.5913. Min Range: -0.5913

Max Act: 0.2757. Min Act: -0.0001

Data Index: 627610 (C4 (Web Text))

Max Activating Token Index: 350

Text #13

Max Range: 0.5913. Min Range: -0.5913

Max Act: 0.2764. Min Act: -0.0001

Data Index: 1054368 (C4 (Web Text))

Max Activating Token Index: 598

Text #14

Max Range: 0.5913. Min Range: -0.5913

Max Act: 0.2786. Min Act: -0.0000

Data Index: 955291 (C4 (Web Text))

Max Activating Token Index: 556

Text #15

Max Range: 0.5913. Min Range: -0.5913

Max Act: 0.3170. Min Act: -0.0001

Data Index: 37230 (C4 (Web Text))

Max Activating Token Index: 618

Text #16

Max Range: 0.5913. Min Range: -0.5913

Max Act: 0.2774. Min Act: -0.0001

Data Index: 1286906 (C4 (Web Text))

Max Activating Token Index: 256

Text #17

Max Range: 0.5913. Min Range: -0.5913

Max Act: 0.2586. Min Act: -0.0001

Data Index: 871897 (C4 (Web Text))

Max Activating Token Index: 688

Text #18

Max Range: 0.5913. Min Range: -0.5913

Max Act: 0.2706. Min Act: -0.0001

Data Index: 273534 (C4 (Web Text))

Max Activating Token Index: 803

Text #19

Max Range: 0.5913. Min Range: -0.5913

Max Act: 0.2739. Min Act: -0.0001

Data Index: 1017584 (C4 (Web Text))

Max Activating Token Index: 845