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

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

Neuron 1411 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2046. Min Range: -2.2046

Max Act: 2.2046. Min Act: -0.0000

Data Index: 5456 (C4 (Web Text))

Max Activating Token Index: 476

Text #1

Max Range: 2.2046. Min Range: -2.2046

Max Act: 2.1118. Min Act: -0.0000

Data Index: 1096034 (C4 (Web Text))

Max Activating Token Index: 366

Text #2

Max Range: 2.2046. Min Range: -2.2046

Max Act: 1.8970. Min Act: -0.0000

Data Index: 41073 (C4 (Web Text))

Max Activating Token Index: 502

Text #3

Max Range: 2.2046. Min Range: -2.2046

Max Act: 2.0020. Min Act: -0.0000

Data Index: 1344765 (C4 (Web Text))

Max Activating Token Index: 61

Text #4

Max Range: 2.2046. Min Range: -2.2046

Max Act: 1.9582. Min Act: -0.0000

Data Index: 833784 (C4 (Web Text))

Max Activating Token Index: 794

Text #5

Max Range: 2.2046. Min Range: -2.2046

Max Act: 1.8068. Min Act: -0.0000

Data Index: 280533 (C4 (Web Text))

Max Activating Token Index: 350

Text #6

Max Range: 2.2046. Min Range: -2.2046

Max Act: 1.8789. Min Act: -0.0000

Data Index: 863032 (C4 (Web Text))

Max Activating Token Index: 351

Text #7

Max Range: 2.2046. Min Range: -2.2046

Max Act: 1.8361. Min Act: -0.0000

Data Index: 77033 (C4 (Web Text))

Max Activating Token Index: 613

Text #8

Max Range: 2.2046. Min Range: -2.2046

Max Act: 1.8292. Min Act: -0.0000

Data Index: 1122761 (C4 (Web Text))

Max Activating Token Index: 717

Text #9

Max Range: 2.2046. Min Range: -2.2046

Max Act: 1.8201. Min Act: -0.0000

Data Index: 544694 (C4 (Web Text))

Max Activating Token Index: 626

Text #10

Max Range: 2.2046. Min Range: -2.2046

Max Act: 1.8163. Min Act: -0.0000

Data Index: 1165000 (C4 (Web Text))

Max Activating Token Index: 605

Text #11

Max Range: 2.2046. Min Range: -2.2046

Max Act: 1.7031. Min Act: -0.0000

Data Index: 634391 (C4 (Web Text))

Max Activating Token Index: 311

Text #12

Max Range: 2.2046. Min Range: -2.2046

Max Act: 1.7929. Min Act: -0.0000

Data Index: 50422 (C4 (Web Text))

Max Activating Token Index: 216

Text #13

Max Range: 2.2046. Min Range: -2.2046

Max Act: 1.7441. Min Act: -0.0000

Data Index: 110970 (C4 (Web Text))

Max Activating Token Index: 456

Text #14

Max Range: 2.2046. Min Range: -2.2046

Max Act: 1.7364. Min Act: -0.0000

Data Index: 837391 (C4 (Web Text))

Max Activating Token Index: 725

Text #15

Max Range: 2.2046. Min Range: -2.2046

Max Act: 1.7338. Min Act: -0.0000

Data Index: 783785 (C4 (Web Text))

Max Activating Token Index: 75

Text #16

Max Range: 2.2046. Min Range: -2.2046

Max Act: 1.5980. Min Act: -0.0000

Data Index: 982769 (C4 (Web Text))

Max Activating Token Index: 987

Text #17

Max Range: 2.2046. Min Range: -2.2046

Max Act: 1.6934. Min Act: -0.0000

Data Index: 993591 (C4 (Web Text))

Max Activating Token Index: 417

Text #18

Max Range: 2.2046. Min Range: -2.2046

Max Act: 1.6785. Min Act: -0.0000

Data Index: 416702 (C4 (Web Text))

Max Activating Token Index: 827

Text #19

Max Range: 2.2046. Min Range: -2.2046

Max Act: 1.6591. Min Act: -0.0000

Data Index: 671607 (C4 (Web Text))

Max Activating Token Index: 270