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

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

Neuron 1721 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: 4.0566. Min Range: -4.0566

Max Act: 4.0476. Min Act: -0.1700

Data Index: 827918 (C4 (Web Text))

Max Activating Token Index: 621

Text #1

Max Range: 4.0566. Min Range: -4.0566

Max Act: 4.0566. Min Act: -0.1647

Data Index: 1311794 (C4 (Web Text))

Max Activating Token Index: 274

Text #2

Max Range: 4.0566. Min Range: -4.0566

Max Act: 3.9816. Min Act: -0.1698

Data Index: 117941 (C4 (Web Text))

Max Activating Token Index: 668

Text #3

Max Range: 4.0566. Min Range: -4.0566

Max Act: 3.9874. Min Act: -0.1686

Data Index: 1037343 (C4 (Web Text))

Max Activating Token Index: 720

Text #4

Max Range: 4.0566. Min Range: -4.0566

Max Act: 3.9758. Min Act: -0.1700

Data Index: 1111426 (C4 (Web Text))

Max Activating Token Index: 519

Text #5

Max Range: 4.0566. Min Range: -4.0566

Max Act: 3.9744. Min Act: -0.1700

Data Index: 251470 (C4 (Web Text))

Max Activating Token Index: 908

Text #6

Max Range: 4.0566. Min Range: -4.0566

Max Act: 3.9031. Min Act: -0.1647

Data Index: 640799 (C4 (Web Text))

Max Activating Token Index: 209

Text #7

Max Range: 4.0566. Min Range: -4.0566

Max Act: 3.9202. Min Act: -0.1647

Data Index: 438092 (C4 (Web Text))

Max Activating Token Index: 260

Text #8

Max Range: 4.0566. Min Range: -4.0566

Max Act: 3.8707. Min Act: -0.1699

Data Index: 1458564 (Python Code)

Max Activating Token Index: 52

Text #9

Max Range: 4.0566. Min Range: -4.0566

Max Act: 3.8733. Min Act: -0.1699

Data Index: 1623385 (Python Code)

Max Activating Token Index: 575

Text #10

Max Range: 4.0566. Min Range: -4.0566

Max Act: 3.8505. Min Act: -0.1698

Data Index: 1378668 (Python Code)

Max Activating Token Index: 954

Text #11

Max Range: 4.0566. Min Range: -4.0566

Max Act: 3.8520. Min Act: -0.1669

Data Index: 1453953 (Python Code)

Max Activating Token Index: 886

Text #12

Max Range: 4.0566. Min Range: -4.0566

Max Act: 3.8425. Min Act: -0.1700

Data Index: 1548493 (Python Code)

Max Activating Token Index: 838

Text #13

Max Range: 4.0566. Min Range: -4.0566

Max Act: 3.8482. Min Act: -0.1698

Data Index: 1537117 (Python Code)

Max Activating Token Index: 453

Text #14

Max Range: 4.0566. Min Range: -4.0566

Max Act: 3.8513. Min Act: -0.1680

Data Index: 1403921 (Python Code)

Max Activating Token Index: 134

Text #15

Max Range: 4.0566. Min Range: -4.0566

Max Act: 3.8264. Min Act: -0.1699

Data Index: 1401720 (Python Code)

Max Activating Token Index: 362

Text #16

Max Range: 4.0566. Min Range: -4.0566

Max Act: 3.8339. Min Act: -0.1647

Data Index: 96533 (C4 (Web Text))

Max Activating Token Index: 127

Text #17

Max Range: 4.0566. Min Range: -4.0566

Max Act: 3.8295. Min Act: -0.1694

Data Index: 950490 (C4 (Web Text))

Max Activating Token Index: 365

Text #18

Max Range: 4.0566. Min Range: -4.0566

Max Act: 3.7916. Min Act: -0.1699

Data Index: 1599937 (Python Code)

Max Activating Token Index: 562

Text #19

Max Range: 4.0566. Min Range: -4.0566

Max Act: 3.8227. Min Act: -0.1647

Data Index: 1519199 (Python Code)

Max Activating Token Index: 128