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

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

Neuron 663 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8452. Min Range: -1.8452

Max Act: 1.8452. Min Act: -0.0000

Data Index: 1004364 (C4 (Web Text))

Max Activating Token Index: 152

Text #1

Max Range: 1.8452. Min Range: -1.8452

Max Act: 1.7817. Min Act: -0.0000

Data Index: 1487560 (Python Code)

Max Activating Token Index: 398

Text #2

Max Range: 1.8452. Min Range: -1.8452

Max Act: 1.5061. Min Act: -0.0000

Data Index: 1498692 (Python Code)

Max Activating Token Index: 312

Text #3

Max Range: 1.8452. Min Range: -1.8452

Max Act: 1.4897. Min Act: -0.0000

Data Index: 801289 (C4 (Web Text))

Max Activating Token Index: 2

Text #4

Max Range: 1.8452. Min Range: -1.8452

Max Act: 1.3962. Min Act: -0.0000

Data Index: 1441109 (Python Code)

Max Activating Token Index: 333

Text #5

Max Range: 1.8452. Min Range: -1.8452

Max Act: 1.4533. Min Act: -0.0000

Data Index: 1484622 (Python Code)

Max Activating Token Index: 409

Text #6

Max Range: 1.8452. Min Range: -1.8452

Max Act: 1.4574. Min Act: -0.0000

Data Index: 1445118 (Python Code)

Max Activating Token Index: 155

Text #7

Max Range: 1.8452. Min Range: -1.8452

Max Act: 1.3989. Min Act: -0.0000

Data Index: 757205 (C4 (Web Text))

Max Activating Token Index: 867

Text #8

Max Range: 1.8452. Min Range: -1.8452

Max Act: 1.4374. Min Act: -0.0000

Data Index: 1094936 (C4 (Web Text))

Max Activating Token Index: 529

Text #9

Max Range: 1.8452. Min Range: -1.8452

Max Act: 1.3879. Min Act: -0.0000

Data Index: 1391067 (Python Code)

Max Activating Token Index: 92

Text #10

Max Range: 1.8452. Min Range: -1.8452

Max Act: 1.3634. Min Act: -0.0000

Data Index: 571314 (C4 (Web Text))

Max Activating Token Index: 803

Text #11

Max Range: 1.8452. Min Range: -1.8452

Max Act: 1.3980. Min Act: -0.0000

Data Index: 1461657 (Python Code)

Max Activating Token Index: 343

Text #12

Max Range: 1.8452. Min Range: -1.8452

Max Act: 1.3477. Min Act: -0.0000

Data Index: 511081 (C4 (Web Text))

Max Activating Token Index: 929

Text #13

Max Range: 1.8452. Min Range: -1.8452

Max Act: 1.3881. Min Act: -0.0000

Data Index: 1333306 (C4 (Web Text))

Max Activating Token Index: 581

Text #14

Max Range: 1.8452. Min Range: -1.8452

Max Act: 1.2692. Min Act: -0.0000

Data Index: 795173 (C4 (Web Text))

Max Activating Token Index: 861

Text #15

Max Range: 1.8452. Min Range: -1.8452

Max Act: 1.4120. Min Act: -0.0000

Data Index: 1363102 (Python Code)

Max Activating Token Index: 802

Text #16

Max Range: 1.8452. Min Range: -1.8452

Max Act: 1.3417. Min Act: -0.0000

Data Index: 1383318 (Python Code)

Max Activating Token Index: 834

Text #17

Max Range: 1.8452. Min Range: -1.8452

Max Act: 1.2966. Min Act: -0.0000

Data Index: 99460 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 1.8452. Min Range: -1.8452

Max Act: 1.2797. Min Act: -0.0000

Data Index: 1564481 (Python Code)

Max Activating Token Index: 367

Text #19

Max Range: 1.8452. Min Range: -1.8452

Max Act: 1.3217. Min Act: -0.0000

Data Index: 1602568 (Python Code)

Max Activating Token Index: 512