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

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

Neuron 3089 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4373. Min Range: -1.4373

Max Act: 1.4373. Min Act: -0.0000

Data Index: 483474 (C4 (Web Text))

Max Activating Token Index: 551

Text #1

Max Range: 1.4373. Min Range: -1.4373

Max Act: 1.3260. Min Act: -0.0000

Data Index: 848548 (C4 (Web Text))

Max Activating Token Index: 951

Text #2

Max Range: 1.4373. Min Range: -1.4373

Max Act: 1.1030. Min Act: 0.0000

Data Index: 632646 (C4 (Web Text))

Max Activating Token Index: 197

Text #3

Max Range: 1.4373. Min Range: -1.4373

Max Act: 1.1072. Min Act: 0.0000

Data Index: 1169002 (C4 (Web Text))

Max Activating Token Index: 449

Text #4

Max Range: 1.4373. Min Range: -1.4373

Max Act: 1.0264. Min Act: -0.0000

Data Index: 642047 (C4 (Web Text))

Max Activating Token Index: 470

Text #5

Max Range: 1.4373. Min Range: -1.4373

Max Act: 0.9682. Min Act: -0.0000

Data Index: 1288519 (C4 (Web Text))

Max Activating Token Index: 936

Text #6

Max Range: 1.4373. Min Range: -1.4373

Max Act: 0.9338. Min Act: -0.0000

Data Index: 1024975 (C4 (Web Text))

Max Activating Token Index: 958

Text #7

Max Range: 1.4373. Min Range: -1.4373

Max Act: 0.9315. Min Act: -0.0000

Data Index: 662750 (C4 (Web Text))

Max Activating Token Index: 347

Text #8

Max Range: 1.4373. Min Range: -1.4373

Max Act: 0.8729. Min Act: -0.0000

Data Index: 1162054 (C4 (Web Text))

Max Activating Token Index: 77

Text #9

Max Range: 1.4373. Min Range: -1.4373

Max Act: 0.9148. Min Act: -0.0000

Data Index: 311222 (C4 (Web Text))

Max Activating Token Index: 11

Text #10

Max Range: 1.4373. Min Range: -1.4373

Max Act: 0.8888. Min Act: -0.0000

Data Index: 520065 (C4 (Web Text))

Max Activating Token Index: 481

Text #11

Max Range: 1.4373. Min Range: -1.4373

Max Act: 0.8428. Min Act: -0.0000

Data Index: 71603 (C4 (Web Text))

Max Activating Token Index: 306

Text #12

Max Range: 1.4373. Min Range: -1.4373

Max Act: 0.8519. Min Act: 0.0001

Data Index: 69007 (C4 (Web Text))

Max Activating Token Index: 68

Text #13

Max Range: 1.4373. Min Range: -1.4373

Max Act: 0.8475. Min Act: 0.0000

Data Index: 733452 (C4 (Web Text))

Max Activating Token Index: 10

Text #14

Max Range: 1.4373. Min Range: -1.4373

Max Act: 0.8148. Min Act: 0.0001

Data Index: 56386 (C4 (Web Text))

Max Activating Token Index: 110

Text #15

Max Range: 1.4373. Min Range: -1.4373

Max Act: 0.8179. Min Act: -0.0000

Data Index: 454366 (C4 (Web Text))

Max Activating Token Index: 292

Text #16

Max Range: 1.4373. Min Range: -1.4373

Max Act: 0.7887. Min Act: -0.0000

Data Index: 337713 (C4 (Web Text))

Max Activating Token Index: 601

Text #17

Max Range: 1.4373. Min Range: -1.4373

Max Act: 0.7659. Min Act: -0.0000

Data Index: 543005 (C4 (Web Text))

Max Activating Token Index: 143

Text #18

Max Range: 1.4373. Min Range: -1.4373

Max Act: 0.7512. Min Act: 0.0000

Data Index: 751356 (C4 (Web Text))

Max Activating Token Index: 944

Text #19

Max Range: 1.4373. Min Range: -1.4373

Max Act: 0.7867. Min Act: -0.0000

Data Index: 167926 (C4 (Web Text))

Max Activating Token Index: 791