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

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

Neuron 580 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4410. Min Range: -0.4410

Max Act: 0.4410. Min Act: -0.0002

Data Index: 1211553 (C4 (Web Text))

Max Activating Token Index: 316

Text #1

Max Range: 0.4410. Min Range: -0.4410

Max Act: 0.4396. Min Act: -0.0002

Data Index: 1217279 (C4 (Web Text))

Max Activating Token Index: 591

Text #2

Max Range: 0.4410. Min Range: -0.4410

Max Act: 0.3112. Min Act: -0.0003

Data Index: 154837 (C4 (Web Text))

Max Activating Token Index: 17

Text #3

Max Range: 0.4410. Min Range: -0.4410

Max Act: 0.3120. Min Act: -0.0002

Data Index: 575472 (C4 (Web Text))

Max Activating Token Index: 953

Text #4

Max Range: 0.4410. Min Range: -0.4410

Max Act: 0.3216. Min Act: -0.0003

Data Index: 1022320 (C4 (Web Text))

Max Activating Token Index: 318

Text #5

Max Range: 0.4410. Min Range: -0.4410

Max Act: 0.3018. Min Act: -0.0003

Data Index: 446198 (C4 (Web Text))

Max Activating Token Index: 26

Text #6

Max Range: 0.4410. Min Range: -0.4410

Max Act: 0.2819. Min Act: -0.0003

Data Index: 214086 (C4 (Web Text))

Max Activating Token Index: 987

Text #7

Max Range: 0.4410. Min Range: -0.4410

Max Act: 0.2725. Min Act: -0.0003

Data Index: 608858 (C4 (Web Text))

Max Activating Token Index: 12

Text #8

Max Range: 0.4410. Min Range: -0.4410

Max Act: 0.2725. Min Act: -0.0002

Data Index: 173572 (C4 (Web Text))

Max Activating Token Index: 596

Text #9

Max Range: 0.4410. Min Range: -0.4410

Max Act: 0.2728. Min Act: -0.0003

Data Index: 587582 (C4 (Web Text))

Max Activating Token Index: 181

Text #10

Max Range: 0.4410. Min Range: -0.4410

Max Act: 0.2667. Min Act: -0.0003

Data Index: 494544 (C4 (Web Text))

Max Activating Token Index: 262

Text #11

Max Range: 0.4410. Min Range: -0.4410

Max Act: 0.2671. Min Act: -0.0003

Data Index: 1318731 (C4 (Web Text))

Max Activating Token Index: 509

Text #12

Max Range: 0.4410. Min Range: -0.4410

Max Act: 0.2646. Min Act: -0.0003

Data Index: 408715 (C4 (Web Text))

Max Activating Token Index: 49

Text #13

Max Range: 0.4410. Min Range: -0.4410

Max Act: 0.2609. Min Act: -0.0003

Data Index: 1032588 (C4 (Web Text))

Max Activating Token Index: 93

Text #14

Max Range: 0.4410. Min Range: -0.4410

Max Act: 0.2689. Min Act: -0.0003

Data Index: 838260 (C4 (Web Text))

Max Activating Token Index: 104

Text #15

Max Range: 0.4410. Min Range: -0.4410

Max Act: 0.2565. Min Act: -0.0003

Data Index: 192153 (C4 (Web Text))

Max Activating Token Index: 82

Text #16

Max Range: 0.4410. Min Range: -0.4410

Max Act: 0.2647. Min Act: -0.0003

Data Index: 847372 (C4 (Web Text))

Max Activating Token Index: 151

Text #17

Max Range: 0.4410. Min Range: -0.4410

Max Act: 0.2560. Min Act: -0.0003

Data Index: 475077 (C4 (Web Text))

Max Activating Token Index: 35

Text #18

Max Range: 0.4410. Min Range: -0.4410

Max Act: 0.2555. Min Act: -0.0003

Data Index: 965130 (C4 (Web Text))

Max Activating Token Index: 53

Text #19

Max Range: 0.4410. Min Range: -0.4410

Max Act: 0.2457. Min Act: -0.0003

Data Index: 1359720 (C4 (Web Text))

Max Activating Token Index: 235