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

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

Neuron 4608 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: 0.8952. Min Range: -0.8952

Max Act: 0.7463. Min Act: -0.0000

Data Index: 1366371 (Python Code)

Max Activating Token Index: 951

Text #1

Max Range: 0.8952. Min Range: -0.8952

Max Act: 0.8651. Min Act: -0.0000

Data Index: 1639785 (Python Code)

Max Activating Token Index: 811

Text #2

Max Range: 0.8952. Min Range: -0.8952

Max Act: 0.8484. Min Act: -0.0000

Data Index: 1374154 (Python Code)

Max Activating Token Index: 648

Text #3

Max Range: 0.8952. Min Range: -0.8952

Max Act: 0.8539. Min Act: -0.0000

Data Index: 1422430 (Python Code)

Max Activating Token Index: 511

Text #4

Max Range: 0.8952. Min Range: -0.8952

Max Act: 0.8014. Min Act: -0.0000

Data Index: 1512752 (Python Code)

Max Activating Token Index: 546

Text #5

Max Range: 0.8952. Min Range: -0.8952

Max Act: 0.8952. Min Act: -0.0000

Data Index: 1501368 (Python Code)

Max Activating Token Index: 984

Text #6

Max Range: 0.8952. Min Range: -0.8952

Max Act: 0.6402. Min Act: -0.0000

Data Index: 1393334 (Python Code)

Max Activating Token Index: 933

Text #7

Max Range: 0.8952. Min Range: -0.8952

Max Act: 0.6512. Min Act: -0.0000

Data Index: 1388325 (Python Code)

Max Activating Token Index: 791

Text #8

Max Range: 0.8952. Min Range: -0.8952

Max Act: 0.6612. Min Act: -0.0000

Data Index: 1436219 (Python Code)

Max Activating Token Index: 758

Text #9

Max Range: 0.8952. Min Range: -0.8952

Max Act: 0.7062. Min Act: -0.0000

Data Index: 1648150 (Python Code)

Max Activating Token Index: 730

Text #10

Max Range: 0.8952. Min Range: -0.8952

Max Act: 0.6709. Min Act: -0.0000

Data Index: 1413811 (Python Code)

Max Activating Token Index: 572

Text #11

Max Range: 0.8952. Min Range: -0.8952

Max Act: 0.6679. Min Act: -0.0000

Data Index: 1516410 (Python Code)

Max Activating Token Index: 605

Text #12

Max Range: 0.8952. Min Range: -0.8952

Max Act: 0.6353. Min Act: -0.0000

Data Index: 1396022 (Python Code)

Max Activating Token Index: 561

Text #13

Max Range: 0.8952. Min Range: -0.8952

Max Act: 0.6539. Min Act: -0.0000

Data Index: 1380111 (Python Code)

Max Activating Token Index: 599

Text #14

Max Range: 0.8952. Min Range: -0.8952

Max Act: 0.6753. Min Act: -0.0000

Data Index: 1550000 (Python Code)

Max Activating Token Index: 60

Text #15

Max Range: 0.8952. Min Range: -0.8952

Max Act: 0.6399. Min Act: -0.0000

Data Index: 1635092 (Python Code)

Max Activating Token Index: 204

Text #16

Max Range: 0.8952. Min Range: -0.8952

Max Act: 0.6487. Min Act: -0.0000

Data Index: 1459190 (Python Code)

Max Activating Token Index: 481

Text #17

Max Range: 0.8952. Min Range: -0.8952

Max Act: 0.6226. Min Act: -0.0000

Data Index: 1603693 (Python Code)

Max Activating Token Index: 207

Text #18

Max Range: 0.8952. Min Range: -0.8952

Max Act: 0.5437. Min Act: -0.0000

Data Index: 1515554 (Python Code)

Max Activating Token Index: 318

Text #19

Max Range: 0.8952. Min Range: -0.8952

Max Act: 0.5956. Min Act: -0.0000

Data Index: 1484197 (Python Code)

Max Activating Token Index: 409