Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2097 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6498. Min Range: -0.6498

Max Act: 0.6498. Min Act: -0.0001

Data Index: 1466086 (Python Code)

Max Activating Token Index: 807

Text #1

Max Range: 0.6498. Min Range: -0.6498

Max Act: 0.5873. Min Act: -0.0001

Data Index: 1617802 (Python Code)

Max Activating Token Index: 802

Text #2

Max Range: 0.6498. Min Range: -0.6498

Max Act: 0.5516. Min Act: -0.0001

Data Index: 1452788 (Python Code)

Max Activating Token Index: 373

Text #3

Max Range: 0.6498. Min Range: -0.6498

Max Act: 0.5322. Min Act: -0.0001

Data Index: 1578129 (Python Code)

Max Activating Token Index: 183

Text #4

Max Range: 0.6498. Min Range: -0.6498

Max Act: 0.4737. Min Act: -0.0001

Data Index: 1423780 (Python Code)

Max Activating Token Index: 545

Text #5

Max Range: 0.6498. Min Range: -0.6498

Max Act: 0.4590. Min Act: -0.0001

Data Index: 1438790 (Python Code)

Max Activating Token Index: 390

Text #6

Max Range: 0.6498. Min Range: -0.6498

Max Act: 0.5123. Min Act: -0.0001

Data Index: 1388917 (Python Code)

Max Activating Token Index: 402

Text #7

Max Range: 0.6498. Min Range: -0.6498

Max Act: 0.4753. Min Act: -0.0001

Data Index: 1419480 (Python Code)

Max Activating Token Index: 384

Text #8

Max Range: 0.6498. Min Range: -0.6498

Max Act: 0.4615. Min Act: -0.0001

Data Index: 1440316 (Python Code)

Max Activating Token Index: 240

Text #9

Max Range: 0.6498. Min Range: -0.6498

Max Act: 0.4884. Min Act: -0.0001

Data Index: 1433631 (Python Code)

Max Activating Token Index: 492

Text #10

Max Range: 0.6498. Min Range: -0.6498

Max Act: 0.4544. Min Act: -0.0001

Data Index: 1615568 (Python Code)

Max Activating Token Index: 313

Text #11

Max Range: 0.6498. Min Range: -0.6498

Max Act: 0.4531. Min Act: -0.0001

Data Index: 1470963 (Python Code)

Max Activating Token Index: 748

Text #12

Max Range: 0.6498. Min Range: -0.6498

Max Act: 0.4688. Min Act: -0.0001

Data Index: 1489076 (Python Code)

Max Activating Token Index: 482

Text #13

Max Range: 0.6498. Min Range: -0.6498

Max Act: 0.4642. Min Act: -0.0001

Data Index: 1544724 (Python Code)

Max Activating Token Index: 429

Text #14

Max Range: 0.6498. Min Range: -0.6498

Max Act: 0.4338. Min Act: -0.0001

Data Index: 1460405 (Python Code)

Max Activating Token Index: 510

Text #15

Max Range: 0.6498. Min Range: -0.6498

Max Act: 0.4605. Min Act: -0.0001

Data Index: 1411098 (Python Code)

Max Activating Token Index: 137

Text #16

Max Range: 0.6498. Min Range: -0.6498

Max Act: 0.4603. Min Act: -0.0001

Data Index: 1580373 (Python Code)

Max Activating Token Index: 229

Text #17

Max Range: 0.6498. Min Range: -0.6498

Max Act: 0.4587. Min Act: -0.0001

Data Index: 1592408 (Python Code)

Max Activating Token Index: 318

Text #18

Max Range: 0.6498. Min Range: -0.6498

Max Act: 0.4373. Min Act: -0.0001

Data Index: 1574091 (Python Code)

Max Activating Token Index: 798

Text #19

Max Range: 0.6498. Min Range: -0.6498

Max Act: 0.4529. Min Act: -0.0001

Data Index: 1373931 (Python Code)

Max Activating Token Index: 802