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

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

Neuron 1488 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: 3.3498. Min Range: -3.3498

Max Act: 3.3498. Min Act: -0.1700

Data Index: 1608648 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 3.3498. Min Range: -3.3498

Max Act: 3.2713. Min Act: -0.1700

Data Index: 1633897 (Python Code)

Max Activating Token Index: 1023

Text #2

Max Range: 3.3498. Min Range: -3.3498

Max Act: 3.2870. Min Act: -0.1700

Data Index: 1485217 (Python Code)

Max Activating Token Index: 1023

Text #3

Max Range: 3.3498. Min Range: -3.3498

Max Act: 3.2398. Min Act: -0.1700

Data Index: 1643794 (Python Code)

Max Activating Token Index: 1023

Text #4

Max Range: 3.3498. Min Range: -3.3498

Max Act: 3.1454. Min Act: -0.1700

Data Index: 1401581 (Python Code)

Max Activating Token Index: 1023

Text #5

Max Range: 3.3498. Min Range: -3.3498

Max Act: 3.1139. Min Act: -0.1700

Data Index: 1547730 (Python Code)

Max Activating Token Index: 1023

Text #6

Max Range: 3.3498. Min Range: -3.3498

Max Act: 3.1297. Min Act: -0.1700

Data Index: 1376207 (Python Code)

Max Activating Token Index: 1023

Text #7

Max Range: 3.3498. Min Range: -3.3498

Max Act: 3.0508. Min Act: -0.1700

Data Index: 1371848 (Python Code)

Max Activating Token Index: 1023

Text #8

Max Range: 3.3498. Min Range: -3.3498

Max Act: 3.0350. Min Act: -0.1700

Data Index: 1566708 (Python Code)

Max Activating Token Index: 1023

Text #9

Max Range: 3.3498. Min Range: -3.3498

Max Act: 3.0350. Min Act: -0.1700

Data Index: 1643096 (Python Code)

Max Activating Token Index: 1023

Text #10

Max Range: 3.3498. Min Range: -3.3498

Max Act: 3.0034. Min Act: -0.1700

Data Index: 488109 (C4 (Web Text))

Max Activating Token Index: 213

Text #11

Max Range: 3.3498. Min Range: -3.3498

Max Act: 3.0034. Min Act: -0.1700

Data Index: 1360466 (Python Code)

Max Activating Token Index: 1023

Text #12

Max Range: 3.3498. Min Range: -3.3498

Max Act: 2.9718. Min Act: -0.1700

Data Index: 439600 (C4 (Web Text))

Max Activating Token Index: 807

Text #13

Max Range: 3.3498. Min Range: -3.3498

Max Act: 2.9718. Min Act: -0.1700

Data Index: 1401687 (Python Code)

Max Activating Token Index: 284

Text #14

Max Range: 3.3498. Min Range: -3.3498

Max Act: 2.9876. Min Act: -0.1700

Data Index: 859214 (C4 (Web Text))

Max Activating Token Index: 40

Text #15

Max Range: 3.3498. Min Range: -3.3498

Max Act: 2.9718. Min Act: -0.1700

Data Index: 153517 (C4 (Web Text))

Max Activating Token Index: 541

Text #16

Max Range: 3.3498. Min Range: -3.3498

Max Act: 2.9243. Min Act: -0.1700

Data Index: 104737 (C4 (Web Text))

Max Activating Token Index: 569

Text #17

Max Range: 3.3498. Min Range: -3.3498

Max Act: 2.9560. Min Act: -0.1700

Data Index: 554201 (C4 (Web Text))

Max Activating Token Index: 368

Text #18

Max Range: 3.3498. Min Range: -3.3498

Max Act: 2.9560. Min Act: -0.1700

Data Index: 297749 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 3.3498. Min Range: -3.3498

Max Act: 2.8926. Min Act: -0.1700

Data Index: 652773 (C4 (Web Text))

Max Activating Token Index: 801