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

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

Neuron 3361 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4894. Min Range: -0.4894

Max Act: 0.4894. Min Act: -0.0001

Data Index: 194062 (C4 (Web Text))

Max Activating Token Index: 80

Text #1

Max Range: 0.4894. Min Range: -0.4894

Max Act: 0.4182. Min Act: -0.0001

Data Index: 430565 (C4 (Web Text))

Max Activating Token Index: 812

Text #2

Max Range: 0.4894. Min Range: -0.4894

Max Act: 0.3994. Min Act: -0.0001

Data Index: 373992 (C4 (Web Text))

Max Activating Token Index: 1022

Text #3

Max Range: 0.4894. Min Range: -0.4894

Max Act: 0.3579. Min Act: -0.0001

Data Index: 685502 (C4 (Web Text))

Max Activating Token Index: 892

Text #4

Max Range: 0.4894. Min Range: -0.4894

Max Act: 0.3750. Min Act: -0.0001

Data Index: 569112 (C4 (Web Text))

Max Activating Token Index: 736

Text #5

Max Range: 0.4894. Min Range: -0.4894

Max Act: 0.3583. Min Act: -0.0001

Data Index: 1091307 (C4 (Web Text))

Max Activating Token Index: 237

Text #6

Max Range: 0.4894. Min Range: -0.4894

Max Act: 0.3357. Min Act: -0.0001

Data Index: 780928 (C4 (Web Text))

Max Activating Token Index: 845

Text #7

Max Range: 0.4894. Min Range: -0.4894

Max Act: 0.3543. Min Act: -0.0001

Data Index: 1213483 (C4 (Web Text))

Max Activating Token Index: 981

Text #8

Max Range: 0.4894. Min Range: -0.4894

Max Act: 0.3439. Min Act: -0.0001

Data Index: 1097546 (C4 (Web Text))

Max Activating Token Index: 44

Text #9

Max Range: 0.4894. Min Range: -0.4894

Max Act: 0.3730. Min Act: -0.0001

Data Index: 453255 (C4 (Web Text))

Max Activating Token Index: 829

Text #10

Max Range: 0.4894. Min Range: -0.4894

Max Act: 0.3556. Min Act: -0.0001

Data Index: 802568 (C4 (Web Text))

Max Activating Token Index: 963

Text #11

Max Range: 0.4894. Min Range: -0.4894

Max Act: 0.3467. Min Act: -0.0001

Data Index: 993420 (C4 (Web Text))

Max Activating Token Index: 209

Text #12

Max Range: 0.4894. Min Range: -0.4894

Max Act: 0.3422. Min Act: -0.0001

Data Index: 845303 (C4 (Web Text))

Max Activating Token Index: 567

Text #13

Max Range: 0.4894. Min Range: -0.4894

Max Act: 0.3418. Min Act: -0.0001

Data Index: 639688 (C4 (Web Text))

Max Activating Token Index: 269

Text #14

Max Range: 0.4894. Min Range: -0.4894

Max Act: 0.3396. Min Act: -0.0001

Data Index: 925274 (C4 (Web Text))

Max Activating Token Index: 280

Text #15

Max Range: 0.4894. Min Range: -0.4894

Max Act: 0.3371. Min Act: -0.0001

Data Index: 921360 (C4 (Web Text))

Max Activating Token Index: 959

Text #16

Max Range: 0.4894. Min Range: -0.4894

Max Act: 0.3454. Min Act: -0.0001

Data Index: 727705 (C4 (Web Text))

Max Activating Token Index: 730

Text #17

Max Range: 0.4894. Min Range: -0.4894

Max Act: 0.3325. Min Act: -0.0001

Data Index: 497117 (C4 (Web Text))

Max Activating Token Index: 1014

Text #18

Max Range: 0.4894. Min Range: -0.4894

Max Act: 0.3126. Min Act: -0.0001

Data Index: 360632 (C4 (Web Text))

Max Activating Token Index: 592

Text #19

Max Range: 0.4894. Min Range: -0.4894

Max Act: 0.3075. Min Act: -0.0001

Data Index: 55842 (C4 (Web Text))

Max Activating Token Index: 41