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

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

Neuron 4945 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.4965. Min Range: -6.4965

Max Act: 6.0634. Min Act: -0.0000

Data Index: 1579188 (Python Code)

Max Activating Token Index: 666

Text #1

Max Range: 6.4965. Min Range: -6.4965

Max Act: 6.2512. Min Act: -0.0000

Data Index: 1384725 (Python Code)

Max Activating Token Index: 241

Text #2

Max Range: 6.4965. Min Range: -6.4965

Max Act: 6.3877. Min Act: -0.0000

Data Index: 1575116 (Python Code)

Max Activating Token Index: 612

Text #3

Max Range: 6.4965. Min Range: -6.4965

Max Act: 6.4965. Min Act: -0.0000

Data Index: 1612590 (Python Code)

Max Activating Token Index: 107

Text #4

Max Range: 6.4965. Min Range: -6.4965

Max Act: 6.2679. Min Act: -0.0000

Data Index: 1423576 (Python Code)

Max Activating Token Index: 276

Text #5

Max Range: 6.4965. Min Range: -6.4965

Max Act: 6.0824. Min Act: -0.0000

Data Index: 1496124 (Python Code)

Max Activating Token Index: 513

Text #6

Max Range: 6.4965. Min Range: -6.4965

Max Act: 5.7306. Min Act: -0.0000

Data Index: 1646787 (Python Code)

Max Activating Token Index: 378

Text #7

Max Range: 6.4965. Min Range: -6.4965

Max Act: 6.0944. Min Act: -0.0000

Data Index: 1442358 (Python Code)

Max Activating Token Index: 818

Text #8

Max Range: 6.4965. Min Range: -6.4965

Max Act: 6.0669. Min Act: -0.0000

Data Index: 1572804 (Python Code)

Max Activating Token Index: 577

Text #9

Max Range: 6.4965. Min Range: -6.4965

Max Act: 5.7201. Min Act: -0.0000

Data Index: 1505311 (Python Code)

Max Activating Token Index: 541

Text #10

Max Range: 6.4965. Min Range: -6.4965

Max Act: 6.2854. Min Act: -0.0000

Data Index: 1560579 (Python Code)

Max Activating Token Index: 372

Text #11

Max Range: 6.4965. Min Range: -6.4965

Max Act: 5.6417. Min Act: -0.0000

Data Index: 1505469 (Python Code)

Max Activating Token Index: 428

Text #12

Max Range: 6.4965. Min Range: -6.4965

Max Act: 5.7145. Min Act: -0.0000

Data Index: 1394445 (Python Code)

Max Activating Token Index: 547

Text #13

Max Range: 6.4965. Min Range: -6.4965

Max Act: 5.5084. Min Act: -0.0000

Data Index: 1553577 (Python Code)

Max Activating Token Index: 650

Text #14

Max Range: 6.4965. Min Range: -6.4965

Max Act: 6.0370. Min Act: -0.0000

Data Index: 1651799 (Python Code)

Max Activating Token Index: 856

Text #15

Max Range: 6.4965. Min Range: -6.4965

Max Act: 5.4660. Min Act: -0.0000

Data Index: 1375016 (Python Code)

Max Activating Token Index: 266

Text #16

Max Range: 6.4965. Min Range: -6.4965

Max Act: 5.4635. Min Act: -0.0000

Data Index: 1526759 (Python Code)

Max Activating Token Index: 300

Text #17

Max Range: 6.4965. Min Range: -6.4965

Max Act: 5.6032. Min Act: -0.0000

Data Index: 1621881 (Python Code)

Max Activating Token Index: 574

Text #18

Max Range: 6.4965. Min Range: -6.4965

Max Act: 5.3825. Min Act: -0.0000

Data Index: 1472727 (Python Code)

Max Activating Token Index: 202

Text #19

Max Range: 6.4965. Min Range: -6.4965

Max Act: 5.5506. Min Act: -0.0000

Data Index: 1656151 (Python Code)

Max Activating Token Index: 443