Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 600 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.4590. Min Range: -3.4590

Max Act: 3.4276. Min Act: -0.1700

Data Index: 1378825 (Python Code)

Max Activating Token Index: 4

Text #1

Max Range: 3.4590. Min Range: -3.4590

Max Act: 3.4590. Min Act: -0.1700

Data Index: 1501912 (Python Code)

Max Activating Token Index: 5

Text #2

Max Range: 3.4590. Min Range: -3.4590

Max Act: 3.3962. Min Act: -0.1700

Data Index: 1439465 (Python Code)

Max Activating Token Index: 3

Text #3

Max Range: 3.4590. Min Range: -3.4590

Max Act: 3.3962. Min Act: -0.1700

Data Index: 1365349 (Python Code)

Max Activating Token Index: 3

Text #4

Max Range: 3.4590. Min Range: -3.4590

Max Act: 3.3962. Min Act: -0.1700

Data Index: 1371870 (Python Code)

Max Activating Token Index: 6

Text #5

Max Range: 3.4590. Min Range: -3.4590

Max Act: 3.3335. Min Act: -0.1700

Data Index: 1495342 (Python Code)

Max Activating Token Index: 4

Text #6

Max Range: 3.4590. Min Range: -3.4590

Max Act: 3.3335. Min Act: -0.1700

Data Index: 1595825 (Python Code)

Max Activating Token Index: 4

Text #7

Max Range: 3.4590. Min Range: -3.4590

Max Act: 3.2864. Min Act: -0.1700

Data Index: 1587177 (Python Code)

Max Activating Token Index: 6

Text #8

Max Range: 3.4590. Min Range: -3.4590

Max Act: 3.2707. Min Act: -0.1700

Data Index: 1377858 (Python Code)

Max Activating Token Index: 4

Text #9

Max Range: 3.4590. Min Range: -3.4590

Max Act: 3.2707. Min Act: -0.1700

Data Index: 1550479 (Python Code)

Max Activating Token Index: 107

Text #10

Max Range: 3.4590. Min Range: -3.4590

Max Act: 3.2549. Min Act: -0.1700

Data Index: 1483999 (Python Code)

Max Activating Token Index: 4

Text #11

Max Range: 3.4590. Min Range: -3.4590

Max Act: 3.2392. Min Act: -0.1700

Data Index: 1399252 (Python Code)

Max Activating Token Index: 245

Text #12

Max Range: 3.4590. Min Range: -3.4590

Max Act: 3.2235. Min Act: -0.1700

Data Index: 1615842 (Python Code)

Max Activating Token Index: 372

Text #13

Max Range: 3.4590. Min Range: -3.4590

Max Act: 3.2235. Min Act: -0.1700

Data Index: 1630626 (Python Code)

Max Activating Token Index: 344

Text #14

Max Range: 3.4590. Min Range: -3.4590

Max Act: 3.2235. Min Act: -0.1700

Data Index: 1449043 (Python Code)

Max Activating Token Index: 589

Text #15

Max Range: 3.4590. Min Range: -3.4590

Max Act: 3.2078. Min Act: -0.1700

Data Index: 1645559 (Python Code)

Max Activating Token Index: 700

Text #16

Max Range: 3.4590. Min Range: -3.4590

Max Act: 3.2078. Min Act: -0.1700

Data Index: 1460109 (Python Code)

Max Activating Token Index: 92

Text #17

Max Range: 3.4590. Min Range: -3.4590

Max Act: 3.2235. Min Act: -0.1700

Data Index: 1456791 (Python Code)

Max Activating Token Index: 3

Text #18

Max Range: 3.4590. Min Range: -3.4590

Max Act: 3.2078. Min Act: -0.1700

Data Index: 1557659 (Python Code)

Max Activating Token Index: 308

Text #19

Max Range: 3.4590. Min Range: -3.4590

Max Act: 3.1920. Min Act: -0.1700

Data Index: 1388992 (Python Code)

Max Activating Token Index: 517