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

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

Neuron 3536 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5507. Min Range: -1.5507

Max Act: 1.5507. Min Act: -0.0001

Data Index: 1067596 (C4 (Web Text))

Max Activating Token Index: 863

Text #1

Max Range: 1.5507. Min Range: -1.5507

Max Act: 1.1789. Min Act: -0.0000

Data Index: 334282 (C4 (Web Text))

Max Activating Token Index: 151

Text #2

Max Range: 1.5507. Min Range: -1.5507

Max Act: 1.0795. Min Act: -0.0001

Data Index: 22643 (C4 (Web Text))

Max Activating Token Index: 268

Text #3

Max Range: 1.5507. Min Range: -1.5507

Max Act: 1.1152. Min Act: -0.0000

Data Index: 816185 (C4 (Web Text))

Max Activating Token Index: 841

Text #4

Max Range: 1.5507. Min Range: -1.5507

Max Act: 1.0888. Min Act: -0.0000

Data Index: 65954 (C4 (Web Text))

Max Activating Token Index: 716

Text #5

Max Range: 1.5507. Min Range: -1.5507

Max Act: 1.0414. Min Act: -0.0000

Data Index: 1246372 (C4 (Web Text))

Max Activating Token Index: 274

Text #6

Max Range: 1.5507. Min Range: -1.5507

Max Act: 0.9788. Min Act: -0.0001

Data Index: 673247 (C4 (Web Text))

Max Activating Token Index: 101

Text #7

Max Range: 1.5507. Min Range: -1.5507

Max Act: 1.1050. Min Act: -0.0000

Data Index: 1641199 (Python Code)

Max Activating Token Index: 503

Text #8

Max Range: 1.5507. Min Range: -1.5507

Max Act: 1.0346. Min Act: -0.0000

Data Index: 698012 (C4 (Web Text))

Max Activating Token Index: 350

Text #9

Max Range: 1.5507. Min Range: -1.5507

Max Act: 0.9702. Min Act: -0.0001

Data Index: 82635 (C4 (Web Text))

Max Activating Token Index: 375

Text #10

Max Range: 1.5507. Min Range: -1.5507

Max Act: 1.0203. Min Act: -0.0001

Data Index: 785461 (C4 (Web Text))

Max Activating Token Index: 96

Text #11

Max Range: 1.5507. Min Range: -1.5507

Max Act: 1.0377. Min Act: -0.0000

Data Index: 1256968 (C4 (Web Text))

Max Activating Token Index: 4

Text #12

Max Range: 1.5507. Min Range: -1.5507

Max Act: 1.0040. Min Act: -0.0000

Data Index: 553080 (C4 (Web Text))

Max Activating Token Index: 223

Text #13

Max Range: 1.5507. Min Range: -1.5507

Max Act: 1.0533. Min Act: -0.0001

Data Index: 957152 (C4 (Web Text))

Max Activating Token Index: 389

Text #14

Max Range: 1.5507. Min Range: -1.5507

Max Act: 1.0388. Min Act: -0.0000

Data Index: 1537830 (Python Code)

Max Activating Token Index: 932

Text #15

Max Range: 1.5507. Min Range: -1.5507

Max Act: 0.9392. Min Act: -0.0000

Data Index: 543310 (C4 (Web Text))

Max Activating Token Index: 269

Text #16

Max Range: 1.5507. Min Range: -1.5507

Max Act: 0.9898. Min Act: -0.0000

Data Index: 290796 (C4 (Web Text))

Max Activating Token Index: 116

Text #17

Max Range: 1.5507. Min Range: -1.5507

Max Act: 0.8810. Min Act: -0.0000

Data Index: 683324 (C4 (Web Text))

Max Activating Token Index: 859

Text #18

Max Range: 1.5507. Min Range: -1.5507

Max Act: 0.9856. Min Act: -0.0000

Data Index: 1222807 (C4 (Web Text))

Max Activating Token Index: 849

Text #19

Max Range: 1.5507. Min Range: -1.5507

Max Act: 1.0146. Min Act: -0.0000

Data Index: 1309124 (C4 (Web Text))

Max Activating Token Index: 125