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

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

Neuron 179 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: 3.0485. Min Range: -3.0485

Max Act: 3.0485. Min Act: -0.1698

Data Index: 891068 (C4 (Web Text))

Max Activating Token Index: 765

Text #1

Max Range: 3.0485. Min Range: -3.0485

Max Act: 3.0387. Min Act: -0.1698

Data Index: 147122 (C4 (Web Text))

Max Activating Token Index: 381

Text #2

Max Range: 3.0485. Min Range: -3.0485

Max Act: 3.0017. Min Act: -0.1700

Data Index: 1401797 (Python Code)

Max Activating Token Index: 382

Text #3

Max Range: 3.0485. Min Range: -3.0485

Max Act: 2.9944. Min Act: -0.1700

Data Index: 1435811 (Python Code)

Max Activating Token Index: 663

Text #4

Max Range: 3.0485. Min Range: -3.0485

Max Act: 2.9584. Min Act: -0.1700

Data Index: 1580539 (Python Code)

Max Activating Token Index: 617

Text #5

Max Range: 3.0485. Min Range: -3.0485

Max Act: 2.9574. Min Act: -0.1698

Data Index: 1557976 (Python Code)

Max Activating Token Index: 304

Text #6

Max Range: 3.0485. Min Range: -3.0485

Max Act: 2.9525. Min Act: -0.1700

Data Index: 1489144 (Python Code)

Max Activating Token Index: 129

Text #7

Max Range: 3.0485. Min Range: -3.0485

Max Act: 2.9503. Min Act: -0.1698

Data Index: 1618419 (Python Code)

Max Activating Token Index: 308

Text #8

Max Range: 3.0485. Min Range: -3.0485

Max Act: 2.9482. Min Act: -0.1700

Data Index: 1519532 (Python Code)

Max Activating Token Index: 229

Text #9

Max Range: 3.0485. Min Range: -3.0485

Max Act: 2.9171. Min Act: -0.1698

Data Index: 56538 (C4 (Web Text))

Max Activating Token Index: 87

Text #10

Max Range: 3.0485. Min Range: -3.0485

Max Act: 2.8967. Min Act: -0.1700

Data Index: 1052775 (C4 (Web Text))

Max Activating Token Index: 64

Text #11

Max Range: 3.0485. Min Range: -3.0485

Max Act: 2.8712. Min Act: -0.1700

Data Index: 873111 (C4 (Web Text))

Max Activating Token Index: 261

Text #12

Max Range: 3.0485. Min Range: -3.0485

Max Act: 2.8553. Min Act: -0.1698

Data Index: 1528850 (Python Code)

Max Activating Token Index: 863

Text #13

Max Range: 3.0485. Min Range: -3.0485

Max Act: 2.8618. Min Act: -0.1700

Data Index: 1366718 (Python Code)

Max Activating Token Index: 774

Text #14

Max Range: 3.0485. Min Range: -3.0485

Max Act: 2.8701. Min Act: -0.1700

Data Index: 830246 (C4 (Web Text))

Max Activating Token Index: 480

Text #15

Max Range: 3.0485. Min Range: -3.0485

Max Act: 2.8379. Min Act: -0.1698

Data Index: 1524902 (Python Code)

Max Activating Token Index: 458

Text #16

Max Range: 3.0485. Min Range: -3.0485

Max Act: 2.8234. Min Act: -0.1700

Data Index: 1574906 (Python Code)

Max Activating Token Index: 219

Text #17

Max Range: 3.0485. Min Range: -3.0485

Max Act: 2.8491. Min Act: -0.1698

Data Index: 1570048 (Python Code)

Max Activating Token Index: 177

Text #18

Max Range: 3.0485. Min Range: -3.0485

Max Act: 2.8330. Min Act: -0.1699

Data Index: 1564088 (Python Code)

Max Activating Token Index: 404

Text #19

Max Range: 3.0485. Min Range: -3.0485

Max Act: 2.8395. Min Act: -0.1698

Data Index: 1409836 (Python Code)

Max Activating Token Index: 933