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

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

Neuron 998 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0374. Min Range: -3.0374

Max Act: 3.0374. Min Act: -0.1700

Data Index: 1438559 (Python Code)

Max Activating Token Index: 367

Text #1

Max Range: 3.0374. Min Range: -3.0374

Max Act: 2.9742. Min Act: -0.1700

Data Index: 1506979 (Python Code)

Max Activating Token Index: 611

Text #2

Max Range: 3.0374. Min Range: -3.0374

Max Act: 2.9584. Min Act: -0.1700

Data Index: 1641597 (Python Code)

Max Activating Token Index: 742

Text #3

Max Range: 3.0374. Min Range: -3.0374

Max Act: 2.9425. Min Act: -0.1700

Data Index: 1479892 (Python Code)

Max Activating Token Index: 909

Text #4

Max Range: 3.0374. Min Range: -3.0374

Max Act: 2.9425. Min Act: -0.1700

Data Index: 1394826 (Python Code)

Max Activating Token Index: 598

Text #5

Max Range: 3.0374. Min Range: -3.0374

Max Act: 2.9267. Min Act: -0.1700

Data Index: 1396563 (Python Code)

Max Activating Token Index: 188

Text #6

Max Range: 3.0374. Min Range: -3.0374

Max Act: 2.8950. Min Act: -0.1700

Data Index: 1415075 (Python Code)

Max Activating Token Index: 395

Text #7

Max Range: 3.0374. Min Range: -3.0374

Max Act: 2.8632. Min Act: -0.1700

Data Index: 1501965 (Python Code)

Max Activating Token Index: 392

Text #8

Max Range: 3.0374. Min Range: -3.0374

Max Act: 2.8473. Min Act: -0.1700

Data Index: 1448086 (Python Code)

Max Activating Token Index: 499

Text #9

Max Range: 3.0374. Min Range: -3.0374

Max Act: 2.8473. Min Act: -0.1700

Data Index: 1383265 (Python Code)

Max Activating Token Index: 707

Text #10

Max Range: 3.0374. Min Range: -3.0374

Max Act: 2.8155. Min Act: -0.1700

Data Index: 1599010 (Python Code)

Max Activating Token Index: 340

Text #11

Max Range: 3.0374. Min Range: -3.0374

Max Act: 2.7677. Min Act: -0.1700

Data Index: 1403644 (Python Code)

Max Activating Token Index: 270

Text #12

Max Range: 3.0374. Min Range: -3.0374

Max Act: 2.7677. Min Act: -0.1700

Data Index: 1502199 (Python Code)

Max Activating Token Index: 484

Text #13

Max Range: 3.0374. Min Range: -3.0374

Max Act: 2.7837. Min Act: -0.1700

Data Index: 1376407 (Python Code)

Max Activating Token Index: 378

Text #14

Max Range: 3.0374. Min Range: -3.0374

Max Act: 2.7677. Min Act: -0.1700

Data Index: 1539927 (Python Code)

Max Activating Token Index: 581

Text #15

Max Range: 3.0374. Min Range: -3.0374

Max Act: 2.7837. Min Act: -0.1700

Data Index: 1393450 (Python Code)

Max Activating Token Index: 670

Text #16

Max Range: 3.0374. Min Range: -3.0374

Max Act: 2.7518. Min Act: -0.1700

Data Index: 1598507 (Python Code)

Max Activating Token Index: 127

Text #17

Max Range: 3.0374. Min Range: -3.0374

Max Act: 2.7358. Min Act: -0.1700

Data Index: 1559922 (Python Code)

Max Activating Token Index: 250

Text #18

Max Range: 3.0374. Min Range: -3.0374

Max Act: 2.7518. Min Act: -0.1700

Data Index: 1553089 (Python Code)

Max Activating Token Index: 624

Text #19

Max Range: 3.0374. Min Range: -3.0374

Max Act: 2.7358. Min Act: -0.1700

Data Index: 1386692 (Python Code)

Max Activating Token Index: 615