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

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

Neuron 3742 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8393. Min Range: -0.8393

Max Act: 0.8393. Min Act: -0.0000

Data Index: 163679 (C4 (Web Text))

Max Activating Token Index: 372

Text #1

Max Range: 0.8393. Min Range: -0.8393

Max Act: 0.7311. Min Act: -0.0000

Data Index: 1100143 (C4 (Web Text))

Max Activating Token Index: 444

Text #2

Max Range: 0.8393. Min Range: -0.8393

Max Act: 0.7264. Min Act: -0.0000

Data Index: 715566 (C4 (Web Text))

Max Activating Token Index: 103

Text #3

Max Range: 0.8393. Min Range: -0.8393

Max Act: 0.7095. Min Act: -0.0000

Data Index: 52286 (C4 (Web Text))

Max Activating Token Index: 155

Text #4

Max Range: 0.8393. Min Range: -0.8393

Max Act: 0.6387. Min Act: -0.0000

Data Index: 504037 (C4 (Web Text))

Max Activating Token Index: 175

Text #5

Max Range: 0.8393. Min Range: -0.8393

Max Act: 0.6418. Min Act: -0.0000

Data Index: 216821 (C4 (Web Text))

Max Activating Token Index: 690

Text #6

Max Range: 0.8393. Min Range: -0.8393

Max Act: 0.6518. Min Act: -0.0000

Data Index: 1348228 (C4 (Web Text))

Max Activating Token Index: 810

Text #7

Max Range: 0.8393. Min Range: -0.8393

Max Act: 0.6913. Min Act: -0.0000

Data Index: 243942 (C4 (Web Text))

Max Activating Token Index: 881

Text #8

Max Range: 0.8393. Min Range: -0.8393

Max Act: 0.5859. Min Act: -0.0000

Data Index: 759592 (C4 (Web Text))

Max Activating Token Index: 837

Text #9

Max Range: 0.8393. Min Range: -0.8393

Max Act: 0.6258. Min Act: -0.0000

Data Index: 1005908 (C4 (Web Text))

Max Activating Token Index: 499

Text #10

Max Range: 0.8393. Min Range: -0.8393

Max Act: 0.6212. Min Act: -0.0000

Data Index: 386652 (C4 (Web Text))

Max Activating Token Index: 388

Text #11

Max Range: 0.8393. Min Range: -0.8393

Max Act: 0.6162. Min Act: -0.0000

Data Index: 932483 (C4 (Web Text))

Max Activating Token Index: 379

Text #12

Max Range: 0.8393. Min Range: -0.8393

Max Act: 0.6136. Min Act: -0.0000

Data Index: 897612 (C4 (Web Text))

Max Activating Token Index: 249

Text #13

Max Range: 0.8393. Min Range: -0.8393

Max Act: 0.6308. Min Act: -0.0000

Data Index: 1259188 (C4 (Web Text))

Max Activating Token Index: 809

Text #14

Max Range: 0.8393. Min Range: -0.8393

Max Act: 0.5858. Min Act: -0.0000

Data Index: 1039693 (C4 (Web Text))

Max Activating Token Index: 875

Text #15

Max Range: 0.8393. Min Range: -0.8393

Max Act: 0.5647. Min Act: -0.0000

Data Index: 871614 (C4 (Web Text))

Max Activating Token Index: 929

Text #16

Max Range: 0.8393. Min Range: -0.8393

Max Act: 0.5514. Min Act: -0.0000

Data Index: 50169 (C4 (Web Text))

Max Activating Token Index: 330

Text #17

Max Range: 0.8393. Min Range: -0.8393

Max Act: 0.5460. Min Act: -0.0000

Data Index: 1284229 (C4 (Web Text))

Max Activating Token Index: 771

Text #18

Max Range: 0.8393. Min Range: -0.8393

Max Act: 0.5547. Min Act: -0.0000

Data Index: 582007 (C4 (Web Text))

Max Activating Token Index: 89

Text #19

Max Range: 0.8393. Min Range: -0.8393

Max Act: 0.5337. Min Act: -0.0000

Data Index: 593189 (C4 (Web Text))

Max Activating Token Index: 420