Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1461 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.5738. Min Range: -5.5738

Max Act: 5.5738. Min Act: -0.1700

Data Index: 1470449 (Python Code)

Max Activating Token Index: 855

Text #1

Max Range: 5.5738. Min Range: -5.5738

Max Act: 5.5738. Min Act: -0.1700

Data Index: 1465291 (Python Code)

Max Activating Token Index: 617

Text #2

Max Range: 5.5738. Min Range: -5.5738

Max Act: 5.5738. Min Act: -0.1700

Data Index: 1633077 (Python Code)

Max Activating Token Index: 668

Text #3

Max Range: 5.5738. Min Range: -5.5738

Max Act: 5.5425. Min Act: -0.1700

Data Index: 1460954 (Python Code)

Max Activating Token Index: 767

Text #4

Max Range: 5.5738. Min Range: -5.5738

Max Act: 5.4800. Min Act: -0.1700

Data Index: 1540026 (Python Code)

Max Activating Token Index: 160

Text #5

Max Range: 5.5738. Min Range: -5.5738

Max Act: 5.5113. Min Act: -0.1700

Data Index: 1574291 (Python Code)

Max Activating Token Index: 521

Text #6

Max Range: 5.5738. Min Range: -5.5738

Max Act: 5.5113. Min Act: -0.1700

Data Index: 1509438 (Python Code)

Max Activating Token Index: 756

Text #7

Max Range: 5.5738. Min Range: -5.5738

Max Act: 5.5113. Min Act: -0.1700

Data Index: 1482400 (Python Code)

Max Activating Token Index: 429

Text #8

Max Range: 5.5738. Min Range: -5.5738

Max Act: 5.4800. Min Act: -0.1700

Data Index: 1638014 (Python Code)

Max Activating Token Index: 73

Text #9

Max Range: 5.5738. Min Range: -5.5738

Max Act: 5.3863. Min Act: -0.1700

Data Index: 1437770 (Python Code)

Max Activating Token Index: 359

Text #10

Max Range: 5.5738. Min Range: -5.5738

Max Act: 5.4175. Min Act: -0.1700

Data Index: 1366221 (Python Code)

Max Activating Token Index: 826

Text #11

Max Range: 5.5738. Min Range: -5.5738

Max Act: 5.3550. Min Act: -0.1700

Data Index: 1433755 (Python Code)

Max Activating Token Index: 984

Text #12

Max Range: 5.5738. Min Range: -5.5738

Max Act: 5.4488. Min Act: -0.1700

Data Index: 1555048 (Python Code)

Max Activating Token Index: 61

Text #13

Max Range: 5.5738. Min Range: -5.5738

Max Act: 5.4175. Min Act: -0.1700

Data Index: 1441406 (Python Code)

Max Activating Token Index: 211

Text #14

Max Range: 5.5738. Min Range: -5.5738

Max Act: 5.4488. Min Act: -0.1700

Data Index: 1617858 (Python Code)

Max Activating Token Index: 587

Text #15

Max Range: 5.5738. Min Range: -5.5738

Max Act: 5.4488. Min Act: -0.1700

Data Index: 1405278 (Python Code)

Max Activating Token Index: 498

Text #16

Max Range: 5.5738. Min Range: -5.5738

Max Act: 5.3863. Min Act: -0.1700

Data Index: 1403297 (Python Code)

Max Activating Token Index: 200

Text #17

Max Range: 5.5738. Min Range: -5.5738

Max Act: 5.4175. Min Act: -0.1700

Data Index: 1504710 (Python Code)

Max Activating Token Index: 220

Text #18

Max Range: 5.5738. Min Range: -5.5738

Max Act: 5.3550. Min Act: -0.1700

Data Index: 1579647 (Python Code)

Max Activating Token Index: 418

Text #19

Max Range: 5.5738. Min Range: -5.5738

Max Act: 5.3550. Min Act: -0.1700

Data Index: 1600118 (Python Code)

Max Activating Token Index: 212