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

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

Neuron 3359 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6488. Min Range: -0.6488

Max Act: 0.6337. Min Act: -0.0000

Data Index: 1514060 (Python Code)

Max Activating Token Index: 601

Text #1

Max Range: 0.6488. Min Range: -0.6488

Max Act: 0.6307. Min Act: -0.0000

Data Index: 1615019 (Python Code)

Max Activating Token Index: 320

Text #2

Max Range: 0.6488. Min Range: -0.6488

Max Act: 0.6314. Min Act: -0.0000

Data Index: 1523417 (Python Code)

Max Activating Token Index: 786

Text #3

Max Range: 0.6488. Min Range: -0.6488

Max Act: 0.6488. Min Act: -0.0000

Data Index: 1474217 (Python Code)

Max Activating Token Index: 197

Text #4

Max Range: 0.6488. Min Range: -0.6488

Max Act: 0.5580. Min Act: -0.0000

Data Index: 1497757 (Python Code)

Max Activating Token Index: 431

Text #5

Max Range: 0.6488. Min Range: -0.6488

Max Act: 0.6000. Min Act: -0.0001

Data Index: 1619582 (Python Code)

Max Activating Token Index: 122

Text #6

Max Range: 0.6488. Min Range: -0.6488

Max Act: 0.5605. Min Act: -0.0001

Data Index: 1412921 (Python Code)

Max Activating Token Index: 334

Text #7

Max Range: 0.6488. Min Range: -0.6488

Max Act: 0.5539. Min Act: -0.0001

Data Index: 1640822 (Python Code)

Max Activating Token Index: 512

Text #8

Max Range: 0.6488. Min Range: -0.6488

Max Act: 0.5749. Min Act: -0.0001

Data Index: 1502052 (Python Code)

Max Activating Token Index: 1011

Text #9

Max Range: 0.6488. Min Range: -0.6488

Max Act: 0.5450. Min Act: -0.0000

Data Index: 1575004 (Python Code)

Max Activating Token Index: 220

Text #10

Max Range: 0.6488. Min Range: -0.6488

Max Act: 0.5517. Min Act: -0.0001

Data Index: 886168 (C4 (Web Text))

Max Activating Token Index: 385

Text #11

Max Range: 0.6488. Min Range: -0.6488

Max Act: 0.4871. Min Act: -0.0001

Data Index: 1591180 (Python Code)

Max Activating Token Index: 591

Text #12

Max Range: 0.6488. Min Range: -0.6488

Max Act: 0.4915. Min Act: -0.0001

Data Index: 1445659 (Python Code)

Max Activating Token Index: 878

Text #13

Max Range: 0.6488. Min Range: -0.6488

Max Act: 0.4667. Min Act: -0.0001

Data Index: 1410426 (Python Code)

Max Activating Token Index: 593

Text #14

Max Range: 0.6488. Min Range: -0.6488

Max Act: 0.4339. Min Act: -0.0000

Data Index: 1468014 (Python Code)

Max Activating Token Index: 544

Text #15

Max Range: 0.6488. Min Range: -0.6488

Max Act: 0.4928. Min Act: -0.0001

Data Index: 1372034 (Python Code)

Max Activating Token Index: 770

Text #16

Max Range: 0.6488. Min Range: -0.6488

Max Act: 0.4771. Min Act: -0.0001

Data Index: 1611656 (Python Code)

Max Activating Token Index: 295

Text #17

Max Range: 0.6488. Min Range: -0.6488

Max Act: 0.4548. Min Act: -0.0001

Data Index: 1405071 (Python Code)

Max Activating Token Index: 804

Text #18

Max Range: 0.6488. Min Range: -0.6488

Max Act: 0.4529. Min Act: -0.0001

Data Index: 1443568 (Python Code)

Max Activating Token Index: 715

Text #19

Max Range: 0.6488. Min Range: -0.6488

Max Act: 0.4552. Min Act: -0.0000

Data Index: 1609331 (Python Code)

Max Activating Token Index: 293