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

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

Neuron 2817 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: 0.7143. Min Range: -0.7143

Max Act: 0.7143. Min Act: -0.0000

Data Index: 829989 (C4 (Web Text))

Max Activating Token Index: 789

Text #1

Max Range: 0.7143. Min Range: -0.7143

Max Act: 0.5898. Min Act: 0.0001

Data Index: 601755 (C4 (Web Text))

Max Activating Token Index: 893

Text #2

Max Range: 0.7143. Min Range: -0.7143

Max Act: 0.5373. Min Act: -0.0000

Data Index: 817409 (C4 (Web Text))

Max Activating Token Index: 797

Text #3

Max Range: 0.7143. Min Range: -0.7143

Max Act: 0.5508. Min Act: -0.0000

Data Index: 809186 (C4 (Web Text))

Max Activating Token Index: 486

Text #4

Max Range: 0.7143. Min Range: -0.7143

Max Act: 0.4872. Min Act: 0.0000

Data Index: 666956 (C4 (Web Text))

Max Activating Token Index: 626

Text #5

Max Range: 0.7143. Min Range: -0.7143

Max Act: 0.4790. Min Act: 0.0000

Data Index: 985763 (C4 (Web Text))

Max Activating Token Index: 496

Text #6

Max Range: 0.7143. Min Range: -0.7143

Max Act: 0.4690. Min Act: -0.0001

Data Index: 353185 (C4 (Web Text))

Max Activating Token Index: 260

Text #7

Max Range: 0.7143. Min Range: -0.7143

Max Act: 0.4699. Min Act: 0.0000

Data Index: 256234 (C4 (Web Text))

Max Activating Token Index: 915

Text #8

Max Range: 0.7143. Min Range: -0.7143

Max Act: 0.4494. Min Act: -0.0000

Data Index: 185053 (C4 (Web Text))

Max Activating Token Index: 408

Text #9

Max Range: 0.7143. Min Range: -0.7143

Max Act: 0.4773. Min Act: -0.0001

Data Index: 436867 (C4 (Web Text))

Max Activating Token Index: 593

Text #10

Max Range: 0.7143. Min Range: -0.7143

Max Act: 0.4232. Min Act: -0.0001

Data Index: 441542 (C4 (Web Text))

Max Activating Token Index: 178

Text #11

Max Range: 0.7143. Min Range: -0.7143

Max Act: 0.4345. Min Act: 0.0000

Data Index: 1579384 (Python Code)

Max Activating Token Index: 958

Text #12

Max Range: 0.7143. Min Range: -0.7143

Max Act: 0.4106. Min Act: -0.0000

Data Index: 477925 (C4 (Web Text))

Max Activating Token Index: 150

Text #13

Max Range: 0.7143. Min Range: -0.7143

Max Act: 0.4075. Min Act: -0.0000

Data Index: 661855 (C4 (Web Text))

Max Activating Token Index: 646

Text #14

Max Range: 0.7143. Min Range: -0.7143

Max Act: 0.4368. Min Act: -0.0000

Data Index: 1031357 (C4 (Web Text))

Max Activating Token Index: 953

Text #15

Max Range: 0.7143. Min Range: -0.7143

Max Act: 0.4261. Min Act: 0.0000

Data Index: 125794 (C4 (Web Text))

Max Activating Token Index: 445

Text #16

Max Range: 0.7143. Min Range: -0.7143

Max Act: 0.4150. Min Act: 0.0001

Data Index: 1124323 (C4 (Web Text))

Max Activating Token Index: 889

Text #17

Max Range: 0.7143. Min Range: -0.7143

Max Act: 0.3972. Min Act: 0.0000

Data Index: 1559622 (Python Code)

Max Activating Token Index: 145

Text #18

Max Range: 0.7143. Min Range: -0.7143

Max Act: 0.4377. Min Act: 0.0001

Data Index: 701328 (C4 (Web Text))

Max Activating Token Index: 881

Text #19

Max Range: 0.7143. Min Range: -0.7143

Max Act: 0.3939. Min Act: -0.0000

Data Index: 1067518 (C4 (Web Text))

Max Activating Token Index: 822