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

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

Neuron 1732 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0688. Min Act: -0.0002

Data Index: 106703 (C4 (Web Text))

Max Activating Token Index: 77

Text #1

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0682. Min Act: -0.0002

Data Index: 169852 (C4 (Web Text))

Max Activating Token Index: 164

Text #2

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0605. Min Act: -0.0002

Data Index: 1255294 (C4 (Web Text))

Max Activating Token Index: 242

Text #3

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0569. Min Act: -0.0002

Data Index: 1065416 (C4 (Web Text))

Max Activating Token Index: 211

Text #4

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0533. Min Act: -0.0002

Data Index: 496484 (C4 (Web Text))

Max Activating Token Index: 632

Text #5

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0551. Min Act: -0.0002

Data Index: 54580 (C4 (Web Text))

Max Activating Token Index: 564

Text #6

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0524. Min Act: -0.0002

Data Index: 1334433 (C4 (Web Text))

Max Activating Token Index: 227

Text #7

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0522. Min Act: -0.0002

Data Index: 115783 (C4 (Web Text))

Max Activating Token Index: 101

Text #8

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0521. Min Act: -0.0002

Data Index: 1097606 (C4 (Web Text))

Max Activating Token Index: 113

Text #9

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0508. Min Act: -0.0002

Data Index: 237717 (C4 (Web Text))

Max Activating Token Index: 194

Text #10

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0514. Min Act: -0.0002

Data Index: 158031 (C4 (Web Text))

Max Activating Token Index: 867

Text #11

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0503. Min Act: -0.0002

Data Index: 1320839 (C4 (Web Text))

Max Activating Token Index: 374

Text #12

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0501. Min Act: -0.0002

Data Index: 1206333 (C4 (Web Text))

Max Activating Token Index: 510

Text #13

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0493. Min Act: -0.0002

Data Index: 1081015 (C4 (Web Text))

Max Activating Token Index: 870

Text #14

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0502. Min Act: -0.0002

Data Index: 53071 (C4 (Web Text))

Max Activating Token Index: 220

Text #15

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0483. Min Act: -0.0002

Data Index: 1273577 (C4 (Web Text))

Max Activating Token Index: 57

Text #16

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0490. Min Act: -0.0002

Data Index: 702470 (C4 (Web Text))

Max Activating Token Index: 841

Text #17

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0479. Min Act: -0.0001

Data Index: 434231 (C4 (Web Text))

Max Activating Token Index: 240

Text #18

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0477. Min Act: -0.0002

Data Index: 1167112 (C4 (Web Text))

Max Activating Token Index: 209

Text #19

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0477. Min Act: -0.0002

Data Index: 698830 (C4 (Web Text))

Max Activating Token Index: 47