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

Dataset: The Pile

Neuron 3814 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.0382. Min Range: -5.0382

Max Act: 5.0382. Min Act: -0.0000

Data Index: 127107 (The Pile)

Max Activating Token Index: 94

Text #1

Max Range: 5.0382. Min Range: -5.0382

Max Act: 3.8213. Min Act: -0.0000

Data Index: 1457910 (The Pile)

Max Activating Token Index: 419

Text #2

Max Range: 5.0382. Min Range: -5.0382

Max Act: 4.0648. Min Act: -0.0000

Data Index: 127100 (The Pile)

Max Activating Token Index: 107

Text #3

Max Range: 5.0382. Min Range: -5.0382

Max Act: 3.8905. Min Act: -0.0000

Data Index: 204706 (The Pile)

Max Activating Token Index: 368

Text #4

Max Range: 5.0382. Min Range: -5.0382

Max Act: 4.4209. Min Act: -0.0000

Data Index: 13687 (The Pile)

Max Activating Token Index: 93

Text #5

Max Range: 5.0382. Min Range: -5.0382

Max Act: 3.7264. Min Act: -0.0000

Data Index: 1532679 (The Pile)

Max Activating Token Index: 691

Text #6

Max Range: 5.0382. Min Range: -5.0382

Max Act: 3.8735. Min Act: -0.0000

Data Index: 1527861 (The Pile)

Max Activating Token Index: 88

Text #7

Max Range: 5.0382. Min Range: -5.0382

Max Act: 3.9893. Min Act: -0.0000

Data Index: 3011 (The Pile)

Max Activating Token Index: 429

Text #8

Max Range: 5.0382. Min Range: -5.0382

Max Act: 3.8146. Min Act: -0.0000

Data Index: 1379472 (The Pile)

Max Activating Token Index: 873

Text #9

Max Range: 5.0382. Min Range: -5.0382

Max Act: 3.9500. Min Act: -0.0000

Data Index: 181575 (The Pile)

Max Activating Token Index: 263

Text #10

Max Range: 5.0382. Min Range: -5.0382

Max Act: 3.5574. Min Act: -0.0000

Data Index: 913851 (The Pile)

Max Activating Token Index: 486

Text #11

Max Range: 5.0382. Min Range: -5.0382

Max Act: 3.6822. Min Act: -0.0000

Data Index: 709292 (The Pile)

Max Activating Token Index: 936

Text #12

Max Range: 5.0382. Min Range: -5.0382

Max Act: 3.5549. Min Act: -0.0000

Data Index: 1903439 (The Pile)

Max Activating Token Index: 472

Text #13

Max Range: 5.0382. Min Range: -5.0382

Max Act: 3.4015. Min Act: -0.0000

Data Index: 346094 (The Pile)

Max Activating Token Index: 84

Text #14

Max Range: 5.0382. Min Range: -5.0382

Max Act: 3.5018. Min Act: -0.0000

Data Index: 1129282 (The Pile)

Max Activating Token Index: 428

Text #15

Max Range: 5.0382. Min Range: -5.0382

Max Act: 3.5744. Min Act: -0.0000

Data Index: 1801145 (The Pile)

Max Activating Token Index: 147

Text #16

Max Range: 5.0382. Min Range: -5.0382

Max Act: 3.4387. Min Act: -0.0000

Data Index: 661612 (The Pile)

Max Activating Token Index: 824

Text #17

Max Range: 5.0382. Min Range: -5.0382

Max Act: 3.4126. Min Act: -0.0000

Data Index: 1182317 (The Pile)

Max Activating Token Index: 185

Text #18

Max Range: 5.0382. Min Range: -5.0382

Max Act: 3.2847. Min Act: -0.0000

Data Index: 948917 (The Pile)

Max Activating Token Index: 675

Text #19

Max Range: 5.0382. Min Range: -5.0382

Max Act: 3.5690. Min Act: -0.0000

Data Index: 117625 (The Pile)

Max Activating Token Index: 806