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

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

Neuron 153 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9142. Min Range: -1.9142

Max Act: 1.9142. Min Act: 0.0001

Data Index: 1581783 (Python Code)

Max Activating Token Index: 285

Text #1

Max Range: 1.9142. Min Range: -1.9142

Max Act: 1.7492. Min Act: 0.0000

Data Index: 1562072 (Python Code)

Max Activating Token Index: 789

Text #2

Max Range: 1.9142. Min Range: -1.9142

Max Act: 1.7444. Min Act: -0.0000

Data Index: 1642378 (Python Code)

Max Activating Token Index: 724

Text #3

Max Range: 1.9142. Min Range: -1.9142

Max Act: 1.3436. Min Act: 0.0000

Data Index: 1545447 (Python Code)

Max Activating Token Index: 471

Text #4

Max Range: 1.9142. Min Range: -1.9142

Max Act: 1.3510. Min Act: -0.0000

Data Index: 1499982 (Python Code)

Max Activating Token Index: 402

Text #5

Max Range: 1.9142. Min Range: -1.9142

Max Act: 1.3347. Min Act: -0.0000

Data Index: 1549681 (Python Code)

Max Activating Token Index: 921

Text #6

Max Range: 1.9142. Min Range: -1.9142

Max Act: 1.2437. Min Act: 0.0001

Data Index: 1572399 (Python Code)

Max Activating Token Index: 839

Text #7

Max Range: 1.9142. Min Range: -1.9142

Max Act: 1.1049. Min Act: -0.0000

Data Index: 1532373 (Python Code)

Max Activating Token Index: 20

Text #8

Max Range: 1.9142. Min Range: -1.9142

Max Act: 0.9547. Min Act: -0.0000

Data Index: 1165321 (C4 (Web Text))

Max Activating Token Index: 859

Text #9

Max Range: 1.9142. Min Range: -1.9142

Max Act: 0.8598. Min Act: -0.0000

Data Index: 1636182 (Python Code)

Max Activating Token Index: 582

Text #10

Max Range: 1.9142. Min Range: -1.9142

Max Act: 0.9111. Min Act: -0.0000

Data Index: 1149095 (C4 (Web Text))

Max Activating Token Index: 152

Text #11

Max Range: 1.9142. Min Range: -1.9142

Max Act: 0.8349. Min Act: -0.0000

Data Index: 1369419 (Python Code)

Max Activating Token Index: 863

Text #12

Max Range: 1.9142. Min Range: -1.9142

Max Act: 0.8618. Min Act: -0.0000

Data Index: 1456968 (Python Code)

Max Activating Token Index: 756

Text #13

Max Range: 1.9142. Min Range: -1.9142

Max Act: 0.7926. Min Act: -0.0000

Data Index: 1567000 (Python Code)

Max Activating Token Index: 479

Text #14

Max Range: 1.9142. Min Range: -1.9142

Max Act: 0.7486. Min Act: 0.0000

Data Index: 1619901 (Python Code)

Max Activating Token Index: 279

Text #15

Max Range: 1.9142. Min Range: -1.9142

Max Act: 0.8030. Min Act: -0.0000

Data Index: 1477008 (Python Code)

Max Activating Token Index: 835

Text #16

Max Range: 1.9142. Min Range: -1.9142

Max Act: 0.8437. Min Act: 0.0000

Data Index: 1602221 (Python Code)

Max Activating Token Index: 149

Text #17

Max Range: 1.9142. Min Range: -1.9142

Max Act: 0.7559. Min Act: -0.0000

Data Index: 1059492 (C4 (Web Text))

Max Activating Token Index: 379

Text #18

Max Range: 1.9142. Min Range: -1.9142

Max Act: 0.7678. Min Act: 0.0000

Data Index: 1467600 (Python Code)

Max Activating Token Index: 355

Text #19

Max Range: 1.9142. Min Range: -1.9142

Max Act: 0.7465. Min Act: -0.0000

Data Index: 1541498 (Python Code)

Max Activating Token Index: 1005