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

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

Neuron 2447 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: 1.1984. Min Range: -1.1984

Max Act: 1.1984. Min Act: -0.0000

Data Index: 466278 (C4 (Web Text))

Max Activating Token Index: 869

Text #1

Max Range: 1.1984. Min Range: -1.1984

Max Act: 0.7019. Min Act: -0.0000

Data Index: 314517 (C4 (Web Text))

Max Activating Token Index: 82

Text #2

Max Range: 1.1984. Min Range: -1.1984

Max Act: 0.6521. Min Act: -0.0000

Data Index: 1536279 (Python Code)

Max Activating Token Index: 388

Text #3

Max Range: 1.1984. Min Range: -1.1984

Max Act: 0.6624. Min Act: -0.0000

Data Index: 149152 (C4 (Web Text))

Max Activating Token Index: 159

Text #4

Max Range: 1.1984. Min Range: -1.1984

Max Act: 0.6495. Min Act: -0.0000

Data Index: 479040 (C4 (Web Text))

Max Activating Token Index: 437

Text #5

Max Range: 1.1984. Min Range: -1.1984

Max Act: 0.6505. Min Act: -0.0000

Data Index: 526257 (C4 (Web Text))

Max Activating Token Index: 883

Text #6

Max Range: 1.1984. Min Range: -1.1984

Max Act: 0.5998. Min Act: -0.0000

Data Index: 314246 (C4 (Web Text))

Max Activating Token Index: 1022

Text #7

Max Range: 1.1984. Min Range: -1.1984

Max Act: 0.5656. Min Act: -0.0000

Data Index: 59669 (C4 (Web Text))

Max Activating Token Index: 352

Text #8

Max Range: 1.1984. Min Range: -1.1984

Max Act: 0.5994. Min Act: -0.0000

Data Index: 222601 (C4 (Web Text))

Max Activating Token Index: 409

Text #9

Max Range: 1.1984. Min Range: -1.1984

Max Act: 0.5658. Min Act: -0.0000

Data Index: 25285 (C4 (Web Text))

Max Activating Token Index: 448

Text #10

Max Range: 1.1984. Min Range: -1.1984

Max Act: 0.5489. Min Act: -0.0000

Data Index: 77750 (C4 (Web Text))

Max Activating Token Index: 249

Text #11

Max Range: 1.1984. Min Range: -1.1984

Max Act: 0.5531. Min Act: -0.0000

Data Index: 888619 (C4 (Web Text))

Max Activating Token Index: 285

Text #12

Max Range: 1.1984. Min Range: -1.1984

Max Act: 0.5953. Min Act: -0.0000

Data Index: 713099 (C4 (Web Text))

Max Activating Token Index: 802

Text #13

Max Range: 1.1984. Min Range: -1.1984

Max Act: 0.5542. Min Act: -0.0000

Data Index: 427264 (C4 (Web Text))

Max Activating Token Index: 816

Text #14

Max Range: 1.1984. Min Range: -1.1984

Max Act: 0.5586. Min Act: -0.0000

Data Index: 1245945 (C4 (Web Text))

Max Activating Token Index: 948

Text #15

Max Range: 1.1984. Min Range: -1.1984

Max Act: 0.5287. Min Act: -0.0000

Data Index: 581436 (C4 (Web Text))

Max Activating Token Index: 730

Text #16

Max Range: 1.1984. Min Range: -1.1984

Max Act: 0.5460. Min Act: -0.0000

Data Index: 92807 (C4 (Web Text))

Max Activating Token Index: 859

Text #17

Max Range: 1.1984. Min Range: -1.1984

Max Act: 0.5220. Min Act: -0.0000

Data Index: 422716 (C4 (Web Text))

Max Activating Token Index: 497

Text #18

Max Range: 1.1984. Min Range: -1.1984

Max Act: 0.4904. Min Act: -0.0000

Data Index: 1441029 (Python Code)

Max Activating Token Index: 686

Text #19

Max Range: 1.1984. Min Range: -1.1984

Max Act: 0.4953. Min Act: -0.0000

Data Index: 242045 (C4 (Web Text))

Max Activating Token Index: 833