Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 906 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 4.0353. Min Range: -4.0353

Max Act: 4.0353. Min Act: -0.1699

Data Index: 481884 (C4 (Web Text))

Max Activating Token Index: 851

Text #1

Max Range: 4.0353. Min Range: -4.0353

Max Act: 4.0189. Min Act: -0.1616

Data Index: 1640978 (Python Code)

Max Activating Token Index: 850

Text #2

Max Range: 4.0353. Min Range: -4.0353

Max Act: 3.9968. Min Act: -0.1700

Data Index: 32660 (C4 (Web Text))

Max Activating Token Index: 295

Text #3

Max Range: 4.0353. Min Range: -4.0353

Max Act: 3.9496. Min Act: -0.1700

Data Index: 737658 (C4 (Web Text))

Max Activating Token Index: 799

Text #4

Max Range: 4.0353. Min Range: -4.0353

Max Act: 3.9424. Min Act: -0.1700

Data Index: 552772 (C4 (Web Text))

Max Activating Token Index: 988

Text #5

Max Range: 4.0353. Min Range: -4.0353

Max Act: 3.9303. Min Act: -0.1700

Data Index: 539070 (C4 (Web Text))

Max Activating Token Index: 466

Text #6

Max Range: 4.0353. Min Range: -4.0353

Max Act: 3.9213. Min Act: -0.1699

Data Index: 1131229 (C4 (Web Text))

Max Activating Token Index: 114

Text #7

Max Range: 4.0353. Min Range: -4.0353

Max Act: 3.8789. Min Act: -0.1700

Data Index: 49076 (C4 (Web Text))

Max Activating Token Index: 588

Text #8

Max Range: 4.0353. Min Range: -4.0353

Max Act: 3.7927. Min Act: -0.1487

Data Index: 1579298 (Python Code)

Max Activating Token Index: 142

Text #9

Max Range: 4.0353. Min Range: -4.0353

Max Act: 3.8011. Min Act: -0.1700

Data Index: 921967 (C4 (Web Text))

Max Activating Token Index: 748

Text #10

Max Range: 4.0353. Min Range: -4.0353

Max Act: 3.7553. Min Act: -0.1700

Data Index: 22611 (C4 (Web Text))

Max Activating Token Index: 1000

Text #11

Max Range: 4.0353. Min Range: -4.0353

Max Act: 3.7486. Min Act: -0.1698

Data Index: 1461597 (Python Code)

Max Activating Token Index: 745

Text #12

Max Range: 4.0353. Min Range: -4.0353

Max Act: 3.7189. Min Act: -0.1700

Data Index: 55465 (C4 (Web Text))

Max Activating Token Index: 349

Text #13

Max Range: 4.0353. Min Range: -4.0353

Max Act: 3.7274. Min Act: -0.1663

Data Index: 1531742 (Python Code)

Max Activating Token Index: 975

Text #14

Max Range: 4.0353. Min Range: -4.0353

Max Act: 3.7082. Min Act: -0.1487

Data Index: 1494065 (Python Code)

Max Activating Token Index: 708

Text #15

Max Range: 4.0353. Min Range: -4.0353

Max Act: 3.6999. Min Act: -0.1487

Data Index: 1482643 (Python Code)

Max Activating Token Index: 175

Text #16

Max Range: 4.0353. Min Range: -4.0353

Max Act: 3.6678. Min Act: -0.1700

Data Index: 380037 (C4 (Web Text))

Max Activating Token Index: 382

Text #17

Max Range: 4.0353. Min Range: -4.0353

Max Act: 3.6791. Min Act: -0.1487

Data Index: 1537429 (Python Code)

Max Activating Token Index: 745

Text #18

Max Range: 4.0353. Min Range: -4.0353

Max Act: 3.6769. Min Act: -0.1695

Data Index: 1509217 (Python Code)

Max Activating Token Index: 1003

Text #19

Max Range: 4.0353. Min Range: -4.0353

Max Act: 3.6687. Min Act: -0.1487

Data Index: 1595470 (Python Code)

Max Activating Token Index: 777