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

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

Neuron 3615 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.6648. Min Range: -1.6648

Max Act: 1.6648. Min Act: -0.0000

Data Index: 551557 (C4 (Web Text))

Max Activating Token Index: 915

Text #1

Max Range: 1.6648. Min Range: -1.6648

Max Act: 1.2089. Min Act: -0.0000

Data Index: 459520 (C4 (Web Text))

Max Activating Token Index: 584

Text #2

Max Range: 1.6648. Min Range: -1.6648

Max Act: 1.1280. Min Act: -0.0000

Data Index: 1348537 (C4 (Web Text))

Max Activating Token Index: 506

Text #3

Max Range: 1.6648. Min Range: -1.6648

Max Act: 0.9602. Min Act: -0.0000

Data Index: 405640 (C4 (Web Text))

Max Activating Token Index: 673

Text #4

Max Range: 1.6648. Min Range: -1.6648

Max Act: 1.0804. Min Act: -0.0000

Data Index: 399604 (C4 (Web Text))

Max Activating Token Index: 108

Text #5

Max Range: 1.6648. Min Range: -1.6648

Max Act: 0.9612. Min Act: -0.0000

Data Index: 682912 (C4 (Web Text))

Max Activating Token Index: 913

Text #6

Max Range: 1.6648. Min Range: -1.6648

Max Act: 0.9082. Min Act: -0.0000

Data Index: 540145 (C4 (Web Text))

Max Activating Token Index: 1017

Text #7

Max Range: 1.6648. Min Range: -1.6648

Max Act: 0.8249. Min Act: -0.0000

Data Index: 272455 (C4 (Web Text))

Max Activating Token Index: 589

Text #8

Max Range: 1.6648. Min Range: -1.6648

Max Act: 0.8083. Min Act: -0.0000

Data Index: 1263615 (C4 (Web Text))

Max Activating Token Index: 560

Text #9

Max Range: 1.6648. Min Range: -1.6648

Max Act: 0.8172. Min Act: -0.0000

Data Index: 456670 (C4 (Web Text))

Max Activating Token Index: 518

Text #10

Max Range: 1.6648. Min Range: -1.6648

Max Act: 0.7209. Min Act: -0.0000

Data Index: 1085522 (C4 (Web Text))

Max Activating Token Index: 846

Text #11

Max Range: 1.6648. Min Range: -1.6648

Max Act: 0.8258. Min Act: -0.0000

Data Index: 893001 (C4 (Web Text))

Max Activating Token Index: 289

Text #12

Max Range: 1.6648. Min Range: -1.6648

Max Act: 0.9020. Min Act: -0.0000

Data Index: 81632 (C4 (Web Text))

Max Activating Token Index: 285

Text #13

Max Range: 1.6648. Min Range: -1.6648

Max Act: 0.8161. Min Act: -0.0000

Data Index: 575846 (C4 (Web Text))

Max Activating Token Index: 740

Text #14

Max Range: 1.6648. Min Range: -1.6648

Max Act: 0.8165. Min Act: -0.0000

Data Index: 78596 (C4 (Web Text))

Max Activating Token Index: 988

Text #15

Max Range: 1.6648. Min Range: -1.6648

Max Act: 0.7847. Min Act: -0.0000

Data Index: 1122440 (C4 (Web Text))

Max Activating Token Index: 507

Text #16

Max Range: 1.6648. Min Range: -1.6648

Max Act: 0.7628. Min Act: -0.0000

Data Index: 1344698 (C4 (Web Text))

Max Activating Token Index: 680

Text #17

Max Range: 1.6648. Min Range: -1.6648

Max Act: 0.7126. Min Act: -0.0000

Data Index: 1043549 (C4 (Web Text))

Max Activating Token Index: 486

Text #18

Max Range: 1.6648. Min Range: -1.6648

Max Act: 0.7678. Min Act: -0.0000

Data Index: 89130 (C4 (Web Text))

Max Activating Token Index: 123

Text #19

Max Range: 1.6648. Min Range: -1.6648

Max Act: 0.6832. Min Act: -0.0000

Data Index: 692186 (C4 (Web Text))

Max Activating Token Index: 272