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

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

Neuron 4800 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8483. Min Range: -1.8483

Max Act: 1.8483. Min Act: -0.0001

Data Index: 300586 (C4 (Web Text))

Max Activating Token Index: 50

Text #1

Max Range: 1.8483. Min Range: -1.8483

Max Act: 1.6769. Min Act: -0.0001

Data Index: 660440 (C4 (Web Text))

Max Activating Token Index: 914

Text #2

Max Range: 1.8483. Min Range: -1.8483

Max Act: 1.6339. Min Act: -0.0001

Data Index: 547782 (C4 (Web Text))

Max Activating Token Index: 76

Text #3

Max Range: 1.8483. Min Range: -1.8483

Max Act: 1.6720. Min Act: -0.0001

Data Index: 130587 (C4 (Web Text))

Max Activating Token Index: 104

Text #4

Max Range: 1.8483. Min Range: -1.8483

Max Act: 1.6399. Min Act: -0.0001

Data Index: 144027 (C4 (Web Text))

Max Activating Token Index: 753

Text #5

Max Range: 1.8483. Min Range: -1.8483

Max Act: 1.5445. Min Act: -0.0001

Data Index: 411187 (C4 (Web Text))

Max Activating Token Index: 88

Text #6

Max Range: 1.8483. Min Range: -1.8483

Max Act: 1.5715. Min Act: -0.0001

Data Index: 63509 (C4 (Web Text))

Max Activating Token Index: 285

Text #7

Max Range: 1.8483. Min Range: -1.8483

Max Act: 1.5533. Min Act: -0.0001

Data Index: 1309354 (C4 (Web Text))

Max Activating Token Index: 687

Text #8

Max Range: 1.8483. Min Range: -1.8483

Max Act: 1.5564. Min Act: -0.0001

Data Index: 599631 (C4 (Web Text))

Max Activating Token Index: 223

Text #9

Max Range: 1.8483. Min Range: -1.8483

Max Act: 1.5032. Min Act: -0.0001

Data Index: 786321 (C4 (Web Text))

Max Activating Token Index: 390

Text #10

Max Range: 1.8483. Min Range: -1.8483

Max Act: 1.3443. Min Act: -0.0001

Data Index: 1143889 (C4 (Web Text))

Max Activating Token Index: 181

Text #11

Max Range: 1.8483. Min Range: -1.8483

Max Act: 1.3810. Min Act: -0.0001

Data Index: 1297548 (C4 (Web Text))

Max Activating Token Index: 203

Text #12

Max Range: 1.8483. Min Range: -1.8483

Max Act: 1.3706. Min Act: -0.0001

Data Index: 477042 (C4 (Web Text))

Max Activating Token Index: 399

Text #13

Max Range: 1.8483. Min Range: -1.8483

Max Act: 1.4054. Min Act: -0.0001

Data Index: 320909 (C4 (Web Text))

Max Activating Token Index: 501

Text #14

Max Range: 1.8483. Min Range: -1.8483

Max Act: 1.3632. Min Act: -0.0001

Data Index: 901749 (C4 (Web Text))

Max Activating Token Index: 538

Text #15

Max Range: 1.8483. Min Range: -1.8483

Max Act: 1.3157. Min Act: -0.0001

Data Index: 1221586 (C4 (Web Text))

Max Activating Token Index: 89

Text #16

Max Range: 1.8483. Min Range: -1.8483

Max Act: 1.3322. Min Act: -0.0001

Data Index: 758010 (C4 (Web Text))

Max Activating Token Index: 301

Text #17

Max Range: 1.8483. Min Range: -1.8483

Max Act: 1.3073. Min Act: -0.0001

Data Index: 826064 (C4 (Web Text))

Max Activating Token Index: 142

Text #18

Max Range: 1.8483. Min Range: -1.8483

Max Act: 1.3438. Min Act: -0.0001

Data Index: 355749 (C4 (Web Text))

Max Activating Token Index: 820

Text #19

Max Range: 1.8483. Min Range: -1.8483

Max Act: 1.3053. Min Act: -0.0001

Data Index: 440489 (C4 (Web Text))

Max Activating Token Index: 519