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

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

Neuron 3906 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8670. Min Range: -0.8670

Max Act: 0.8455. Min Act: -0.0000

Data Index: 301018 (C4 (Web Text))

Max Activating Token Index: 14

Text #1

Max Range: 0.8670. Min Range: -0.8670

Max Act: 0.8670. Min Act: -0.0000

Data Index: 91917 (C4 (Web Text))

Max Activating Token Index: 144

Text #2

Max Range: 0.8670. Min Range: -0.8670

Max Act: 0.8124. Min Act: -0.0000

Data Index: 222581 (C4 (Web Text))

Max Activating Token Index: 140

Text #3

Max Range: 0.8670. Min Range: -0.8670

Max Act: 0.6840. Min Act: -0.0000

Data Index: 192594 (C4 (Web Text))

Max Activating Token Index: 271

Text #4

Max Range: 0.8670. Min Range: -0.8670

Max Act: 0.6971. Min Act: -0.0000

Data Index: 970159 (C4 (Web Text))

Max Activating Token Index: 163

Text #5

Max Range: 0.8670. Min Range: -0.8670

Max Act: 0.6874. Min Act: -0.0000

Data Index: 1040981 (C4 (Web Text))

Max Activating Token Index: 987

Text #6

Max Range: 0.8670. Min Range: -0.8670

Max Act: 0.5847. Min Act: -0.0000

Data Index: 1324720 (C4 (Web Text))

Max Activating Token Index: 994

Text #7

Max Range: 0.8670. Min Range: -0.8670

Max Act: 0.5554. Min Act: -0.0000

Data Index: 593034 (C4 (Web Text))

Max Activating Token Index: 534

Text #8

Max Range: 0.8670. Min Range: -0.8670

Max Act: 0.5718. Min Act: -0.0000

Data Index: 695373 (C4 (Web Text))

Max Activating Token Index: 358

Text #9

Max Range: 0.8670. Min Range: -0.8670

Max Act: 0.5401. Min Act: -0.0000

Data Index: 317565 (C4 (Web Text))

Max Activating Token Index: 712

Text #10

Max Range: 0.8670. Min Range: -0.8670

Max Act: 0.5287. Min Act: -0.0000

Data Index: 1305220 (C4 (Web Text))

Max Activating Token Index: 330

Text #11

Max Range: 0.8670. Min Range: -0.8670

Max Act: 0.5403. Min Act: -0.0000

Data Index: 1198851 (C4 (Web Text))

Max Activating Token Index: 312

Text #12

Max Range: 0.8670. Min Range: -0.8670

Max Act: 0.5406. Min Act: -0.0000

Data Index: 248443 (C4 (Web Text))

Max Activating Token Index: 218

Text #13

Max Range: 0.8670. Min Range: -0.8670

Max Act: 0.5234. Min Act: -0.0000

Data Index: 452707 (C4 (Web Text))

Max Activating Token Index: 638

Text #14

Max Range: 0.8670. Min Range: -0.8670

Max Act: 0.4994. Min Act: -0.0000

Data Index: 176544 (C4 (Web Text))

Max Activating Token Index: 296

Text #15

Max Range: 0.8670. Min Range: -0.8670

Max Act: 0.5098. Min Act: -0.0000

Data Index: 539825 (C4 (Web Text))

Max Activating Token Index: 22

Text #16

Max Range: 0.8670. Min Range: -0.8670

Max Act: 0.4800. Min Act: -0.0000

Data Index: 1246891 (C4 (Web Text))

Max Activating Token Index: 166

Text #17

Max Range: 0.8670. Min Range: -0.8670

Max Act: 0.4889. Min Act: -0.0000

Data Index: 390579 (C4 (Web Text))

Max Activating Token Index: 522

Text #18

Max Range: 0.8670. Min Range: -0.8670

Max Act: 0.5084. Min Act: -0.0000

Data Index: 81760 (C4 (Web Text))

Max Activating Token Index: 968

Text #19

Max Range: 0.8670. Min Range: -0.8670

Max Act: 0.5001. Min Act: -0.0000

Data Index: 1320323 (C4 (Web Text))

Max Activating Token Index: 10