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

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

Neuron 2398 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.4131. Min Range: -1.4131

Max Act: 1.4131. Min Act: -0.0001

Data Index: 148474 (C4 (Web Text))

Max Activating Token Index: 295

Text #1

Max Range: 1.4131. Min Range: -1.4131

Max Act: 1.1575. Min Act: -0.0000

Data Index: 1255666 (C4 (Web Text))

Max Activating Token Index: 425

Text #2

Max Range: 1.4131. Min Range: -1.4131

Max Act: 0.9428. Min Act: -0.0001

Data Index: 723084 (C4 (Web Text))

Max Activating Token Index: 250

Text #3

Max Range: 1.4131. Min Range: -1.4131

Max Act: 0.9286. Min Act: -0.0001

Data Index: 796651 (C4 (Web Text))

Max Activating Token Index: 67

Text #4

Max Range: 1.4131. Min Range: -1.4131

Max Act: 0.8919. Min Act: -0.0000

Data Index: 861599 (C4 (Web Text))

Max Activating Token Index: 44

Text #5

Max Range: 1.4131. Min Range: -1.4131

Max Act: 0.8840. Min Act: -0.0000

Data Index: 1231538 (C4 (Web Text))

Max Activating Token Index: 556

Text #6

Max Range: 1.4131. Min Range: -1.4131

Max Act: 0.8581. Min Act: -0.0001

Data Index: 566559 (C4 (Web Text))

Max Activating Token Index: 958

Text #7

Max Range: 1.4131. Min Range: -1.4131

Max Act: 0.8352. Min Act: -0.0000

Data Index: 713369 (C4 (Web Text))

Max Activating Token Index: 312

Text #8

Max Range: 1.4131. Min Range: -1.4131

Max Act: 0.8261. Min Act: -0.0001

Data Index: 681229 (C4 (Web Text))

Max Activating Token Index: 165

Text #9

Max Range: 1.4131. Min Range: -1.4131

Max Act: 0.7861. Min Act: -0.0001

Data Index: 695284 (C4 (Web Text))

Max Activating Token Index: 724

Text #10

Max Range: 1.4131. Min Range: -1.4131

Max Act: 0.8454. Min Act: -0.0001

Data Index: 387423 (C4 (Web Text))

Max Activating Token Index: 386

Text #11

Max Range: 1.4131. Min Range: -1.4131

Max Act: 0.8330. Min Act: -0.0001

Data Index: 483412 (C4 (Web Text))

Max Activating Token Index: 680

Text #12

Max Range: 1.4131. Min Range: -1.4131

Max Act: 0.8078. Min Act: -0.0001

Data Index: 476576 (C4 (Web Text))

Max Activating Token Index: 877

Text #13

Max Range: 1.4131. Min Range: -1.4131

Max Act: 0.9597. Min Act: -0.0000

Data Index: 289243 (C4 (Web Text))

Max Activating Token Index: 927

Text #14

Max Range: 1.4131. Min Range: -1.4131

Max Act: 0.8427. Min Act: -0.0000

Data Index: 647201 (C4 (Web Text))

Max Activating Token Index: 819

Text #15

Max Range: 1.4131. Min Range: -1.4131

Max Act: 0.8728. Min Act: -0.0001

Data Index: 980805 (C4 (Web Text))

Max Activating Token Index: 281

Text #16

Max Range: 1.4131. Min Range: -1.4131

Max Act: 0.8079. Min Act: -0.0001

Data Index: 13571 (C4 (Web Text))

Max Activating Token Index: 168

Text #17

Max Range: 1.4131. Min Range: -1.4131

Max Act: 0.8530. Min Act: -0.0001

Data Index: 755768 (C4 (Web Text))

Max Activating Token Index: 405

Text #18

Max Range: 1.4131. Min Range: -1.4131

Max Act: 0.8209. Min Act: -0.0001

Data Index: 409078 (C4 (Web Text))

Max Activating Token Index: 444

Text #19

Max Range: 1.4131. Min Range: -1.4131

Max Act: 0.7722. Min Act: -0.0001

Data Index: 1153214 (C4 (Web Text))

Max Activating Token Index: 434