Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1634 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4932. Min Range: -0.4932

Max Act: 0.4932. Min Act: -0.0000

Data Index: 451131 (C4 (Web Text))

Max Activating Token Index: 558

Text #1

Max Range: 0.4932. Min Range: -0.4932

Max Act: 0.4557. Min Act: -0.0001

Data Index: 562873 (C4 (Web Text))

Max Activating Token Index: 914

Text #2

Max Range: 0.4932. Min Range: -0.4932

Max Act: 0.4642. Min Act: -0.0000

Data Index: 740558 (C4 (Web Text))

Max Activating Token Index: 153

Text #3

Max Range: 0.4932. Min Range: -0.4932

Max Act: 0.4354. Min Act: -0.0000

Data Index: 535995 (C4 (Web Text))

Max Activating Token Index: 468

Text #4

Max Range: 0.4932. Min Range: -0.4932

Max Act: 0.4192. Min Act: -0.0000

Data Index: 452373 (C4 (Web Text))

Max Activating Token Index: 481

Text #5

Max Range: 0.4932. Min Range: -0.4932

Max Act: 0.3721. Min Act: -0.0001

Data Index: 1215764 (C4 (Web Text))

Max Activating Token Index: 688

Text #6

Max Range: 0.4932. Min Range: -0.4932

Max Act: 0.4125. Min Act: -0.0000

Data Index: 1180413 (C4 (Web Text))

Max Activating Token Index: 268

Text #7

Max Range: 0.4932. Min Range: -0.4932

Max Act: 0.4398. Min Act: -0.0001

Data Index: 570758 (C4 (Web Text))

Max Activating Token Index: 192

Text #8

Max Range: 0.4932. Min Range: -0.4932

Max Act: 0.4029. Min Act: -0.0000

Data Index: 1170364 (C4 (Web Text))

Max Activating Token Index: 142

Text #9

Max Range: 0.4932. Min Range: -0.4932

Max Act: 0.4021. Min Act: -0.0001

Data Index: 950728 (C4 (Web Text))

Max Activating Token Index: 516

Text #10

Max Range: 0.4932. Min Range: -0.4932

Max Act: 0.3957. Min Act: -0.0000

Data Index: 1065328 (C4 (Web Text))

Max Activating Token Index: 350

Text #11

Max Range: 0.4932. Min Range: -0.4932

Max Act: 0.4087. Min Act: -0.0000

Data Index: 795874 (C4 (Web Text))

Max Activating Token Index: 311

Text #12

Max Range: 0.4932. Min Range: -0.4932

Max Act: 0.3988. Min Act: -0.0000

Data Index: 700387 (C4 (Web Text))

Max Activating Token Index: 667

Text #13

Max Range: 0.4932. Min Range: -0.4932

Max Act: 0.3979. Min Act: -0.0000

Data Index: 427605 (C4 (Web Text))

Max Activating Token Index: 462

Text #14

Max Range: 0.4932. Min Range: -0.4932

Max Act: 0.3827. Min Act: -0.0000

Data Index: 217846 (C4 (Web Text))

Max Activating Token Index: 158

Text #15

Max Range: 0.4932. Min Range: -0.4932

Max Act: 0.3814. Min Act: -0.0001

Data Index: 1139882 (C4 (Web Text))

Max Activating Token Index: 783

Text #16

Max Range: 0.4932. Min Range: -0.4932

Max Act: 0.3922. Min Act: -0.0000

Data Index: 847637 (C4 (Web Text))

Max Activating Token Index: 465

Text #17

Max Range: 0.4932. Min Range: -0.4932

Max Act: 0.3884. Min Act: -0.0000

Data Index: 530080 (C4 (Web Text))

Max Activating Token Index: 441

Text #18

Max Range: 0.4932. Min Range: -0.4932

Max Act: 0.3879. Min Act: -0.0000

Data Index: 810298 (C4 (Web Text))

Max Activating Token Index: 577

Text #19

Max Range: 0.4932. Min Range: -0.4932

Max Act: 0.3864. Min Act: -0.0000

Data Index: 814783 (C4 (Web Text))

Max Activating Token Index: 635