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

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

Neuron 3415 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.6315. Min Range: -4.6315

Max Act: 4.6315. Min Act: -0.0000

Data Index: 1150469 (C4 (Web Text))

Max Activating Token Index: 917

Text #1

Max Range: 4.6315. Min Range: -4.6315

Max Act: 4.2733. Min Act: -0.0001

Data Index: 981291 (C4 (Web Text))

Max Activating Token Index: 330

Text #2

Max Range: 4.6315. Min Range: -4.6315

Max Act: 4.0175. Min Act: -0.0000

Data Index: 1275038 (C4 (Web Text))

Max Activating Token Index: 512

Text #3

Max Range: 4.6315. Min Range: -4.6315

Max Act: 3.8210. Min Act: -0.0000

Data Index: 382364 (C4 (Web Text))

Max Activating Token Index: 601

Text #4

Max Range: 4.6315. Min Range: -4.6315

Max Act: 3.0310. Min Act: -0.0001

Data Index: 641987 (C4 (Web Text))

Max Activating Token Index: 907

Text #5

Max Range: 4.6315. Min Range: -4.6315

Max Act: 2.8680. Min Act: -0.0000

Data Index: 145474 (C4 (Web Text))

Max Activating Token Index: 889

Text #6

Max Range: 4.6315. Min Range: -4.6315

Max Act: 3.0944. Min Act: -0.0001

Data Index: 638699 (C4 (Web Text))

Max Activating Token Index: 88

Text #7

Max Range: 4.6315. Min Range: -4.6315

Max Act: 2.9230. Min Act: -0.0000

Data Index: 1306652 (C4 (Web Text))

Max Activating Token Index: 367

Text #8

Max Range: 4.6315. Min Range: -4.6315

Max Act: 2.9166. Min Act: -0.0001

Data Index: 1353950 (C4 (Web Text))

Max Activating Token Index: 104

Text #9

Max Range: 4.6315. Min Range: -4.6315

Max Act: 2.8696. Min Act: -0.0000

Data Index: 1032750 (C4 (Web Text))

Max Activating Token Index: 124

Text #10

Max Range: 4.6315. Min Range: -4.6315

Max Act: 2.8273. Min Act: -0.0000

Data Index: 967409 (C4 (Web Text))

Max Activating Token Index: 910

Text #11

Max Range: 4.6315. Min Range: -4.6315

Max Act: 3.1038. Min Act: -0.0001

Data Index: 944041 (C4 (Web Text))

Max Activating Token Index: 1005

Text #12

Max Range: 4.6315. Min Range: -4.6315

Max Act: 3.0996. Min Act: -0.0001

Data Index: 107747 (C4 (Web Text))

Max Activating Token Index: 714

Text #13

Max Range: 4.6315. Min Range: -4.6315

Max Act: 2.8853. Min Act: -0.0000

Data Index: 191699 (C4 (Web Text))

Max Activating Token Index: 785

Text #14

Max Range: 4.6315. Min Range: -4.6315

Max Act: 2.8639. Min Act: -0.0001

Data Index: 583482 (C4 (Web Text))

Max Activating Token Index: 266

Text #15

Max Range: 4.6315. Min Range: -4.6315

Max Act: 2.8836. Min Act: -0.0000

Data Index: 518035 (C4 (Web Text))

Max Activating Token Index: 70

Text #16

Max Range: 4.6315. Min Range: -4.6315

Max Act: 2.9026. Min Act: -0.0000

Data Index: 1358901 (C4 (Web Text))

Max Activating Token Index: 905

Text #17

Max Range: 4.6315. Min Range: -4.6315

Max Act: 2.5455. Min Act: -0.0001

Data Index: 780716 (C4 (Web Text))

Max Activating Token Index: 556

Text #18

Max Range: 4.6315. Min Range: -4.6315

Max Act: 2.7020. Min Act: -0.0001

Data Index: 854590 (C4 (Web Text))

Max Activating Token Index: 858

Text #19

Max Range: 4.6315. Min Range: -4.6315

Max Act: 2.6716. Min Act: -0.0000

Data Index: 199575 (C4 (Web Text))

Max Activating Token Index: 803