Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1087 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0377. Min Act: -0.0005

Data Index: 968484 (C4 (Web Text))

Max Activating Token Index: 438

Text #1

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0354. Min Act: -0.0005

Data Index: 520075 (C4 (Web Text))

Max Activating Token Index: 789

Text #2

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0352. Min Act: -0.0005

Data Index: 944144 (C4 (Web Text))

Max Activating Token Index: 562

Text #3

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0332. Min Act: -0.0005

Data Index: 1046065 (C4 (Web Text))

Max Activating Token Index: 662

Text #4

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0332. Min Act: -0.0005

Data Index: 1054466 (C4 (Web Text))

Max Activating Token Index: 80

Text #5

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0329. Min Act: -0.0005

Data Index: 351968 (C4 (Web Text))

Max Activating Token Index: 357

Text #6

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0333. Min Act: -0.0005

Data Index: 851220 (C4 (Web Text))

Max Activating Token Index: 495

Text #7

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0333. Min Act: -0.0005

Data Index: 1252988 (C4 (Web Text))

Max Activating Token Index: 990

Text #8

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0336. Min Act: -0.0005

Data Index: 556029 (C4 (Web Text))

Max Activating Token Index: 850

Text #9

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0323. Min Act: -0.0005

Data Index: 610616 (C4 (Web Text))

Max Activating Token Index: 638

Text #10

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0326. Min Act: -0.0005

Data Index: 63433 (C4 (Web Text))

Max Activating Token Index: 401

Text #11

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0326. Min Act: -0.0005

Data Index: 425947 (C4 (Web Text))

Max Activating Token Index: 764

Text #12

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0324. Min Act: -0.0005

Data Index: 17055 (C4 (Web Text))

Max Activating Token Index: 922

Text #13

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0315. Min Act: -0.0005

Data Index: 506297 (C4 (Web Text))

Max Activating Token Index: 306

Text #14

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0326. Min Act: -0.0005

Data Index: 518100 (C4 (Web Text))

Max Activating Token Index: 296

Text #15

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0320. Min Act: -0.0005

Data Index: 818127 (C4 (Web Text))

Max Activating Token Index: 472

Text #16

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0322. Min Act: -0.0005

Data Index: 899408 (C4 (Web Text))

Max Activating Token Index: 254

Text #17

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0321. Min Act: -0.0005

Data Index: 948309 (C4 (Web Text))

Max Activating Token Index: 86

Text #18

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0315. Min Act: -0.0005

Data Index: 947318 (C4 (Web Text))

Max Activating Token Index: 184

Text #19

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0320. Min Act: -0.0005

Data Index: 713242 (C4 (Web Text))

Max Activating Token Index: 305