Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2659 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3215. Min Range: -0.3215

Max Act: 0.3215. Min Act: -0.0001

Data Index: 105402 (C4 (Web Text))

Max Activating Token Index: 176

Text #1

Max Range: 0.3215. Min Range: -0.3215

Max Act: 0.2763. Min Act: -0.0001

Data Index: 24124 (C4 (Web Text))

Max Activating Token Index: 387

Text #2

Max Range: 0.3215. Min Range: -0.3215

Max Act: 0.2681. Min Act: -0.0001

Data Index: 729047 (C4 (Web Text))

Max Activating Token Index: 958

Text #3

Max Range: 0.3215. Min Range: -0.3215

Max Act: 0.2743. Min Act: -0.0001

Data Index: 621727 (C4 (Web Text))

Max Activating Token Index: 68

Text #4

Max Range: 0.3215. Min Range: -0.3215

Max Act: 0.2405. Min Act: -0.0001

Data Index: 712371 (C4 (Web Text))

Max Activating Token Index: 674

Text #5

Max Range: 0.3215. Min Range: -0.3215

Max Act: 0.2238. Min Act: -0.0001

Data Index: 131598 (C4 (Web Text))

Max Activating Token Index: 699

Text #6

Max Range: 0.3215. Min Range: -0.3215

Max Act: 0.2525. Min Act: -0.0001

Data Index: 788538 (C4 (Web Text))

Max Activating Token Index: 764

Text #7

Max Range: 0.3215. Min Range: -0.3215

Max Act: 0.2293. Min Act: -0.0001

Data Index: 619943 (C4 (Web Text))

Max Activating Token Index: 218

Text #8

Max Range: 0.3215. Min Range: -0.3215

Max Act: 0.2506. Min Act: -0.0001

Data Index: 720770 (C4 (Web Text))

Max Activating Token Index: 927

Text #9

Max Range: 0.3215. Min Range: -0.3215

Max Act: 0.2314. Min Act: -0.0001

Data Index: 1029255 (C4 (Web Text))

Max Activating Token Index: 485

Text #10

Max Range: 0.3215. Min Range: -0.3215

Max Act: 0.2282. Min Act: -0.0001

Data Index: 778207 (C4 (Web Text))

Max Activating Token Index: 520

Text #11

Max Range: 0.3215. Min Range: -0.3215

Max Act: 0.2238. Min Act: -0.0001

Data Index: 1229937 (C4 (Web Text))

Max Activating Token Index: 76

Text #12

Max Range: 0.3215. Min Range: -0.3215

Max Act: 0.2381. Min Act: -0.0001

Data Index: 430616 (C4 (Web Text))

Max Activating Token Index: 1004

Text #13

Max Range: 0.3215. Min Range: -0.3215

Max Act: 0.2215. Min Act: -0.0000

Data Index: 463629 (C4 (Web Text))

Max Activating Token Index: 169

Text #14

Max Range: 0.3215. Min Range: -0.3215

Max Act: 0.2239. Min Act: -0.0001

Data Index: 45855 (C4 (Web Text))

Max Activating Token Index: 961

Text #15

Max Range: 0.3215. Min Range: -0.3215

Max Act: 0.2194. Min Act: -0.0001

Data Index: 841585 (C4 (Web Text))

Max Activating Token Index: 837

Text #16

Max Range: 0.3215. Min Range: -0.3215

Max Act: 0.1971. Min Act: -0.0001

Data Index: 17263 (C4 (Web Text))

Max Activating Token Index: 828

Text #17

Max Range: 0.3215. Min Range: -0.3215

Max Act: 0.2051. Min Act: -0.0001

Data Index: 73666 (C4 (Web Text))

Max Activating Token Index: 636

Text #18

Max Range: 0.3215. Min Range: -0.3215

Max Act: 0.2104. Min Act: -0.0001

Data Index: 554519 (C4 (Web Text))

Max Activating Token Index: 381

Text #19

Max Range: 0.3215. Min Range: -0.3215

Max Act: 0.1890. Min Act: -0.0001

Data Index: 326867 (C4 (Web Text))

Max Activating Token Index: 371