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

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

Neuron 1064 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6309. Min Range: -3.6309

Max Act: 3.6309. Min Act: -0.1700

Data Index: 1626499 (Python Code)

Max Activating Token Index: 454

Text #1

Max Range: 3.6309. Min Range: -3.6309

Max Act: 3.5056. Min Act: -0.1700

Data Index: 1548036 (Python Code)

Max Activating Token Index: 1023

Text #2

Max Range: 3.6309. Min Range: -3.6309

Max Act: 3.4743. Min Act: -0.1700

Data Index: 1481335 (Python Code)

Max Activating Token Index: 380

Text #3

Max Range: 3.6309. Min Range: -3.6309

Max Act: 3.4429. Min Act: -0.1700

Data Index: 1548136 (Python Code)

Max Activating Token Index: 383

Text #4

Max Range: 3.6309. Min Range: -3.6309

Max Act: 3.4899. Min Act: -0.1700

Data Index: 1571804 (Python Code)

Max Activating Token Index: 409

Text #5

Max Range: 3.6309. Min Range: -3.6309

Max Act: 3.4116. Min Act: -0.1700

Data Index: 1495782 (Python Code)

Max Activating Token Index: 469

Text #6

Max Range: 3.6309. Min Range: -3.6309

Max Act: 3.3488. Min Act: -0.1700

Data Index: 1531287 (Python Code)

Max Activating Token Index: 863

Text #7

Max Range: 3.6309. Min Range: -3.6309

Max Act: 3.4586. Min Act: -0.1700

Data Index: 1559192 (Python Code)

Max Activating Token Index: 791

Text #8

Max Range: 3.6309. Min Range: -3.6309

Max Act: 3.4429. Min Act: -0.1700

Data Index: 1392225 (Python Code)

Max Activating Token Index: 594

Text #9

Max Range: 3.6309. Min Range: -3.6309

Max Act: 3.4586. Min Act: -0.1700

Data Index: 1614422 (Python Code)

Max Activating Token Index: 492

Text #10

Max Range: 3.6309. Min Range: -3.6309

Max Act: 3.4116. Min Act: -0.1700

Data Index: 1457454 (Python Code)

Max Activating Token Index: 445

Text #11

Max Range: 3.6309. Min Range: -3.6309

Max Act: 3.4743. Min Act: -0.1700

Data Index: 1468638 (Python Code)

Max Activating Token Index: 1023

Text #12

Max Range: 3.6309. Min Range: -3.6309

Max Act: 3.3645. Min Act: -0.1700

Data Index: 1424224 (Python Code)

Max Activating Token Index: 483

Text #13

Max Range: 3.6309. Min Range: -3.6309

Max Act: 3.4272. Min Act: -0.1700

Data Index: 1547028 (Python Code)

Max Activating Token Index: 492

Text #14

Max Range: 3.6309. Min Range: -3.6309

Max Act: 3.3488. Min Act: -0.1700

Data Index: 1367367 (Python Code)

Max Activating Token Index: 503

Text #15

Max Range: 3.6309. Min Range: -3.6309

Max Act: 3.3488. Min Act: -0.1700

Data Index: 1399640 (Python Code)

Max Activating Token Index: 560

Text #16

Max Range: 3.6309. Min Range: -3.6309

Max Act: 3.2860. Min Act: -0.1700

Data Index: 1406279 (Python Code)

Max Activating Token Index: 357

Text #17

Max Range: 3.6309. Min Range: -3.6309

Max Act: 3.3488. Min Act: -0.1700

Data Index: 1524230 (Python Code)

Max Activating Token Index: 1023

Text #18

Max Range: 3.6309. Min Range: -3.6309

Max Act: 3.2860. Min Act: -0.1700

Data Index: 1543135 (Python Code)

Max Activating Token Index: 331

Text #19

Max Range: 3.6309. Min Range: -3.6309

Max Act: 3.3331. Min Act: -0.1700

Data Index: 1493808 (Python Code)

Max Activating Token Index: 176