Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1835 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.1763. Min Range: -2.1763

Max Act: 2.1763. Min Act: -0.0000

Data Index: 1395521 (Python Code)

Max Activating Token Index: 211

Text #1

Max Range: 2.1763. Min Range: -2.1763

Max Act: 1.3408. Min Act: -0.0000

Data Index: 1424701 (Python Code)

Max Activating Token Index: 829

Text #2

Max Range: 2.1763. Min Range: -2.1763

Max Act: 1.1804. Min Act: -0.0000

Data Index: 1594573 (Python Code)

Max Activating Token Index: 1002

Text #3

Max Range: 2.1763. Min Range: -2.1763

Max Act: 1.2683. Min Act: -0.0000

Data Index: 1522587 (Python Code)

Max Activating Token Index: 959

Text #4

Max Range: 2.1763. Min Range: -2.1763

Max Act: 1.2286. Min Act: -0.0000

Data Index: 1571152 (Python Code)

Max Activating Token Index: 1016

Text #5

Max Range: 2.1763. Min Range: -2.1763

Max Act: 1.1512. Min Act: -0.0000

Data Index: 1600279 (Python Code)

Max Activating Token Index: 269

Text #6

Max Range: 2.1763. Min Range: -2.1763

Max Act: 1.1674. Min Act: -0.0000

Data Index: 1609629 (Python Code)

Max Activating Token Index: 956

Text #7

Max Range: 2.1763. Min Range: -2.1763

Max Act: 1.3270. Min Act: -0.0000

Data Index: 1476949 (Python Code)

Max Activating Token Index: 823

Text #8

Max Range: 2.1763. Min Range: -2.1763

Max Act: 1.1585. Min Act: -0.0000

Data Index: 1464533 (Python Code)

Max Activating Token Index: 463

Text #9

Max Range: 2.1763. Min Range: -2.1763

Max Act: 1.0557. Min Act: -0.0000

Data Index: 1491804 (Python Code)

Max Activating Token Index: 1019

Text #10

Max Range: 2.1763. Min Range: -2.1763

Max Act: 1.1840. Min Act: -0.0000

Data Index: 1359969 (Python Code)

Max Activating Token Index: 331

Text #11

Max Range: 2.1763. Min Range: -2.1763

Max Act: 1.0545. Min Act: -0.0000

Data Index: 1398225 (Python Code)

Max Activating Token Index: 557

Text #12

Max Range: 2.1763. Min Range: -2.1763

Max Act: 0.9978. Min Act: -0.0000

Data Index: 1578295 (Python Code)

Max Activating Token Index: 450

Text #13

Max Range: 2.1763. Min Range: -2.1763

Max Act: 0.7794. Min Act: -0.0000

Data Index: 1543285 (Python Code)

Max Activating Token Index: 853

Text #14

Max Range: 2.1763. Min Range: -2.1763

Max Act: 0.9442. Min Act: -0.0000

Data Index: 1422260 (Python Code)

Max Activating Token Index: 57

Text #15

Max Range: 2.1763. Min Range: -2.1763

Max Act: 0.8463. Min Act: -0.0000

Data Index: 1532405 (Python Code)

Max Activating Token Index: 252

Text #16

Max Range: 2.1763. Min Range: -2.1763

Max Act: 0.9161. Min Act: -0.0000

Data Index: 1466202 (Python Code)

Max Activating Token Index: 472

Text #17

Max Range: 2.1763. Min Range: -2.1763

Max Act: 1.0526. Min Act: -0.0000

Data Index: 1641442 (Python Code)

Max Activating Token Index: 366

Text #18

Max Range: 2.1763. Min Range: -2.1763

Max Act: 0.9847. Min Act: -0.0000

Data Index: 1542479 (Python Code)

Max Activating Token Index: 415

Text #19

Max Range: 2.1763. Min Range: -2.1763

Max Act: 0.9417. Min Act: -0.0000

Data Index: 1373095 (Python Code)

Max Activating Token Index: 132