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

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

Neuron 838 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: 1.6861. Min Range: -1.6861

Max Act: 1.6861. Min Act: -0.0000

Data Index: 177411 (C4 (Web Text))

Max Activating Token Index: 472

Text #1

Max Range: 1.6861. Min Range: -1.6861

Max Act: 1.6039. Min Act: -0.0000

Data Index: 335773 (C4 (Web Text))

Max Activating Token Index: 569

Text #2

Max Range: 1.6861. Min Range: -1.6861

Max Act: 1.5903. Min Act: -0.0000

Data Index: 1129858 (C4 (Web Text))

Max Activating Token Index: 135

Text #3

Max Range: 1.6861. Min Range: -1.6861

Max Act: 1.5994. Min Act: -0.0000

Data Index: 64893 (C4 (Web Text))

Max Activating Token Index: 87

Text #4

Max Range: 1.6861. Min Range: -1.6861

Max Act: 1.5426. Min Act: -0.0000

Data Index: 1338821 (C4 (Web Text))

Max Activating Token Index: 925

Text #5

Max Range: 1.6861. Min Range: -1.6861

Max Act: 1.4680. Min Act: -0.0000

Data Index: 1090830 (C4 (Web Text))

Max Activating Token Index: 281

Text #6

Max Range: 1.6861. Min Range: -1.6861

Max Act: 1.5004. Min Act: -0.0000

Data Index: 1600456 (Python Code)

Max Activating Token Index: 860

Text #7

Max Range: 1.6861. Min Range: -1.6861

Max Act: 1.4394. Min Act: -0.0000

Data Index: 894568 (C4 (Web Text))

Max Activating Token Index: 872

Text #8

Max Range: 1.6861. Min Range: -1.6861

Max Act: 1.4510. Min Act: -0.0000

Data Index: 254948 (C4 (Web Text))

Max Activating Token Index: 347

Text #9

Max Range: 1.6861. Min Range: -1.6861

Max Act: 1.4144. Min Act: -0.0000

Data Index: 102559 (C4 (Web Text))

Max Activating Token Index: 649

Text #10

Max Range: 1.6861. Min Range: -1.6861

Max Act: 1.4092. Min Act: -0.0000

Data Index: 78605 (C4 (Web Text))

Max Activating Token Index: 335

Text #11

Max Range: 1.6861. Min Range: -1.6861

Max Act: 1.3771. Min Act: -0.0000

Data Index: 1262313 (C4 (Web Text))

Max Activating Token Index: 171

Text #12

Max Range: 1.6861. Min Range: -1.6861

Max Act: 1.3917. Min Act: -0.0000

Data Index: 357290 (C4 (Web Text))

Max Activating Token Index: 681

Text #13

Max Range: 1.6861. Min Range: -1.6861

Max Act: 1.3669. Min Act: -0.0000

Data Index: 120037 (C4 (Web Text))

Max Activating Token Index: 485

Text #14

Max Range: 1.6861. Min Range: -1.6861

Max Act: 1.3665. Min Act: -0.0000

Data Index: 1622543 (Python Code)

Max Activating Token Index: 885

Text #15

Max Range: 1.6861. Min Range: -1.6861

Max Act: 1.4285. Min Act: -0.0000

Data Index: 865154 (C4 (Web Text))

Max Activating Token Index: 170

Text #16

Max Range: 1.6861. Min Range: -1.6861

Max Act: 1.3317. Min Act: -0.0000

Data Index: 690554 (C4 (Web Text))

Max Activating Token Index: 690

Text #17

Max Range: 1.6861. Min Range: -1.6861

Max Act: 1.3544. Min Act: -0.0000

Data Index: 1126305 (C4 (Web Text))

Max Activating Token Index: 228

Text #18

Max Range: 1.6861. Min Range: -1.6861

Max Act: 1.3664. Min Act: -0.0000

Data Index: 746933 (C4 (Web Text))

Max Activating Token Index: 939

Text #19

Max Range: 1.6861. Min Range: -1.6861

Max Act: 1.2837. Min Act: -0.0000

Data Index: 506863 (C4 (Web Text))

Max Activating Token Index: 101