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

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

Neuron 1255 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3870. Min Range: -0.3870

Max Act: 0.3714. Min Act: -0.0000

Data Index: 660052 (C4 (Web Text))

Max Activating Token Index: 923

Text #1

Max Range: 0.3870. Min Range: -0.3870

Max Act: 0.3870. Min Act: -0.0001

Data Index: 732522 (C4 (Web Text))

Max Activating Token Index: 626

Text #2

Max Range: 0.3870. Min Range: -0.3870

Max Act: 0.3512. Min Act: -0.0000

Data Index: 123178 (C4 (Web Text))

Max Activating Token Index: 955

Text #3

Max Range: 0.3870. Min Range: -0.3870

Max Act: 0.3526. Min Act: -0.0000

Data Index: 1138864 (C4 (Web Text))

Max Activating Token Index: 709

Text #4

Max Range: 0.3870. Min Range: -0.3870

Max Act: 0.3477. Min Act: -0.0000

Data Index: 925804 (C4 (Web Text))

Max Activating Token Index: 457

Text #5

Max Range: 0.3870. Min Range: -0.3870

Max Act: 0.3478. Min Act: -0.0001

Data Index: 309778 (C4 (Web Text))

Max Activating Token Index: 984

Text #6

Max Range: 0.3870. Min Range: -0.3870

Max Act: 0.3691. Min Act: -0.0000

Data Index: 281492 (C4 (Web Text))

Max Activating Token Index: 326

Text #7

Max Range: 0.3870. Min Range: -0.3870

Max Act: 0.3393. Min Act: -0.0001

Data Index: 517951 (C4 (Web Text))

Max Activating Token Index: 703

Text #8

Max Range: 0.3870. Min Range: -0.3870

Max Act: 0.3444. Min Act: -0.0000

Data Index: 122009 (C4 (Web Text))

Max Activating Token Index: 613

Text #9

Max Range: 0.3870. Min Range: -0.3870

Max Act: 0.3348. Min Act: -0.0000

Data Index: 1265299 (C4 (Web Text))

Max Activating Token Index: 673

Text #10

Max Range: 0.3870. Min Range: -0.3870

Max Act: 0.3418. Min Act: -0.0000

Data Index: 545790 (C4 (Web Text))

Max Activating Token Index: 855

Text #11

Max Range: 0.3870. Min Range: -0.3870

Max Act: 0.3141. Min Act: -0.0000

Data Index: 1278014 (C4 (Web Text))

Max Activating Token Index: 876

Text #12

Max Range: 0.3870. Min Range: -0.3870

Max Act: 0.2994. Min Act: -0.0000

Data Index: 199250 (C4 (Web Text))

Max Activating Token Index: 373

Text #13

Max Range: 0.3870. Min Range: -0.3870

Max Act: 0.3003. Min Act: -0.0000

Data Index: 1010421 (C4 (Web Text))

Max Activating Token Index: 577

Text #14

Max Range: 0.3870. Min Range: -0.3870

Max Act: 0.3014. Min Act: -0.0000

Data Index: 1504738 (Python Code)

Max Activating Token Index: 988

Text #15

Max Range: 0.3870. Min Range: -0.3870

Max Act: 0.2996. Min Act: -0.0001

Data Index: 1469868 (Python Code)

Max Activating Token Index: 763

Text #16

Max Range: 0.3870. Min Range: -0.3870

Max Act: 0.3008. Min Act: -0.0000

Data Index: 349350 (C4 (Web Text))

Max Activating Token Index: 993

Text #17

Max Range: 0.3870. Min Range: -0.3870

Max Act: 0.2886. Min Act: -0.0001

Data Index: 1015453 (C4 (Web Text))

Max Activating Token Index: 949

Text #18

Max Range: 0.3870. Min Range: -0.3870

Max Act: 0.2933. Min Act: -0.0001

Data Index: 988355 (C4 (Web Text))

Max Activating Token Index: 577

Text #19

Max Range: 0.3870. Min Range: -0.3870

Max Act: 0.3021. Min Act: -0.0000

Data Index: 621235 (C4 (Web Text))

Max Activating Token Index: 822