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

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

Neuron 2900 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.2935. Min Range: -4.2935

Max Act: 4.2935. Min Act: -0.0001

Data Index: 65000 (C4 (Web Text))

Max Activating Token Index: 105

Text #1

Max Range: 4.2935. Min Range: -4.2935

Max Act: 3.5609. Min Act: -0.0000

Data Index: 1059948 (C4 (Web Text))

Max Activating Token Index: 734

Text #2

Max Range: 4.2935. Min Range: -4.2935

Max Act: 3.6914. Min Act: -0.0001

Data Index: 1236501 (C4 (Web Text))

Max Activating Token Index: 996

Text #3

Max Range: 4.2935. Min Range: -4.2935

Max Act: 3.6420. Min Act: -0.0000

Data Index: 477691 (C4 (Web Text))

Max Activating Token Index: 767

Text #4

Max Range: 4.2935. Min Range: -4.2935

Max Act: 3.4737. Min Act: -0.0000

Data Index: 190818 (C4 (Web Text))

Max Activating Token Index: 71

Text #5

Max Range: 4.2935. Min Range: -4.2935

Max Act: 3.0066. Min Act: -0.0001

Data Index: 155806 (C4 (Web Text))

Max Activating Token Index: 327

Text #6

Max Range: 4.2935. Min Range: -4.2935

Max Act: 2.9632. Min Act: -0.0001

Data Index: 353289 (C4 (Web Text))

Max Activating Token Index: 940

Text #7

Max Range: 4.2935. Min Range: -4.2935

Max Act: 2.9360. Min Act: -0.0001

Data Index: 922164 (C4 (Web Text))

Max Activating Token Index: 935

Text #8

Max Range: 4.2935. Min Range: -4.2935

Max Act: 2.7954. Min Act: -0.0001

Data Index: 747608 (C4 (Web Text))

Max Activating Token Index: 701

Text #9

Max Range: 4.2935. Min Range: -4.2935

Max Act: 2.8364. Min Act: -0.0000

Data Index: 432193 (C4 (Web Text))

Max Activating Token Index: 142

Text #10

Max Range: 4.2935. Min Range: -4.2935

Max Act: 2.5392. Min Act: -0.0000

Data Index: 815789 (C4 (Web Text))

Max Activating Token Index: 358

Text #11

Max Range: 4.2935. Min Range: -4.2935

Max Act: 2.6385. Min Act: -0.0000

Data Index: 203653 (C4 (Web Text))

Max Activating Token Index: 353

Text #12

Max Range: 4.2935. Min Range: -4.2935

Max Act: 2.4947. Min Act: -0.0001

Data Index: 207892 (C4 (Web Text))

Max Activating Token Index: 881

Text #13

Max Range: 4.2935. Min Range: -4.2935

Max Act: 2.5502. Min Act: -0.0000

Data Index: 1224900 (C4 (Web Text))

Max Activating Token Index: 614

Text #14

Max Range: 4.2935. Min Range: -4.2935

Max Act: 2.6589. Min Act: -0.0000

Data Index: 1283039 (C4 (Web Text))

Max Activating Token Index: 732

Text #15

Max Range: 4.2935. Min Range: -4.2935

Max Act: 2.5253. Min Act: -0.0001

Data Index: 251377 (C4 (Web Text))

Max Activating Token Index: 676

Text #16

Max Range: 4.2935. Min Range: -4.2935

Max Act: 2.5244. Min Act: -0.0001

Data Index: 720505 (C4 (Web Text))

Max Activating Token Index: 387

Text #17

Max Range: 4.2935. Min Range: -4.2935

Max Act: 2.3235. Min Act: -0.0001

Data Index: 497940 (C4 (Web Text))

Max Activating Token Index: 803

Text #18

Max Range: 4.2935. Min Range: -4.2935

Max Act: 2.5216. Min Act: -0.0000

Data Index: 1161155 (C4 (Web Text))

Max Activating Token Index: 931

Text #19

Max Range: 4.2935. Min Range: -4.2935

Max Act: 2.5077. Min Act: -0.0001

Data Index: 892088 (C4 (Web Text))

Max Activating Token Index: 165