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

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

Neuron 5558 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: 2.8878. Min Range: -2.8878

Max Act: 2.8300. Min Act: -0.0000

Data Index: 1115355 (C4 (Web Text))

Max Activating Token Index: 74

Text #1

Max Range: 2.8878. Min Range: -2.8878

Max Act: 2.8878. Min Act: -0.0000

Data Index: 423450 (C4 (Web Text))

Max Activating Token Index: 127

Text #2

Max Range: 2.8878. Min Range: -2.8878

Max Act: 2.8163. Min Act: -0.0000

Data Index: 847157 (C4 (Web Text))

Max Activating Token Index: 427

Text #3

Max Range: 2.8878. Min Range: -2.8878

Max Act: 2.8077. Min Act: -0.0000

Data Index: 1153671 (C4 (Web Text))

Max Activating Token Index: 303

Text #4

Max Range: 2.8878. Min Range: -2.8878

Max Act: 2.8105. Min Act: -0.0000

Data Index: 102264 (C4 (Web Text))

Max Activating Token Index: 329

Text #5

Max Range: 2.8878. Min Range: -2.8878

Max Act: 2.7486. Min Act: -0.0000

Data Index: 338294 (C4 (Web Text))

Max Activating Token Index: 517

Text #6

Max Range: 2.8878. Min Range: -2.8878

Max Act: 2.8776. Min Act: -0.0000

Data Index: 66178 (C4 (Web Text))

Max Activating Token Index: 493

Text #7

Max Range: 2.8878. Min Range: -2.8878

Max Act: 2.6466. Min Act: -0.0000

Data Index: 378128 (C4 (Web Text))

Max Activating Token Index: 185

Text #8

Max Range: 2.8878. Min Range: -2.8878

Max Act: 2.6214. Min Act: -0.0000

Data Index: 389266 (C4 (Web Text))

Max Activating Token Index: 391

Text #9

Max Range: 2.8878. Min Range: -2.8878

Max Act: 2.6094. Min Act: -0.0000

Data Index: 107463 (C4 (Web Text))

Max Activating Token Index: 89

Text #10

Max Range: 2.8878. Min Range: -2.8878

Max Act: 2.5300. Min Act: -0.0000

Data Index: 1468701 (Python Code)

Max Activating Token Index: 638

Text #11

Max Range: 2.8878. Min Range: -2.8878

Max Act: 2.3939. Min Act: -0.0000

Data Index: 264692 (C4 (Web Text))

Max Activating Token Index: 801

Text #12

Max Range: 2.8878. Min Range: -2.8878

Max Act: 2.3524. Min Act: -0.0000

Data Index: 49589 (C4 (Web Text))

Max Activating Token Index: 195

Text #13

Max Range: 2.8878. Min Range: -2.8878

Max Act: 2.3554. Min Act: -0.0000

Data Index: 747134 (C4 (Web Text))

Max Activating Token Index: 824

Text #14

Max Range: 2.8878. Min Range: -2.8878

Max Act: 2.3532. Min Act: -0.0000

Data Index: 1174556 (C4 (Web Text))

Max Activating Token Index: 361

Text #15

Max Range: 2.8878. Min Range: -2.8878

Max Act: 2.4433. Min Act: -0.0000

Data Index: 310435 (C4 (Web Text))

Max Activating Token Index: 201

Text #16

Max Range: 2.8878. Min Range: -2.8878

Max Act: 2.2991. Min Act: -0.0000

Data Index: 988546 (C4 (Web Text))

Max Activating Token Index: 856

Text #17

Max Range: 2.8878. Min Range: -2.8878

Max Act: 2.4093. Min Act: -0.0000

Data Index: 1355047 (C4 (Web Text))

Max Activating Token Index: 94

Text #18

Max Range: 2.8878. Min Range: -2.8878

Max Act: 2.4137. Min Act: -0.0000

Data Index: 57738 (C4 (Web Text))

Max Activating Token Index: 446

Text #19

Max Range: 2.8878. Min Range: -2.8878

Max Act: 2.2838. Min Act: -0.0000

Data Index: 1614686 (Python Code)

Max Activating Token Index: 172