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

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

Neuron 300 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: 3.4115. Min Range: -3.4115

Max Act: 3.4115. Min Act: -0.1700

Data Index: 1558193 (Python Code)

Max Activating Token Index: 514

Text #1

Max Range: 3.4115. Min Range: -3.4115

Max Act: 3.3728. Min Act: -0.1471

Data Index: 1296562 (C4 (Web Text))

Max Activating Token Index: 527

Text #2

Max Range: 3.4115. Min Range: -3.4115

Max Act: 3.3849. Min Act: -0.1699

Data Index: 1562854 (Python Code)

Max Activating Token Index: 333

Text #3

Max Range: 3.4115. Min Range: -3.4115

Max Act: 3.3808. Min Act: -0.1621

Data Index: 1614316 (Python Code)

Max Activating Token Index: 622

Text #4

Max Range: 3.4115. Min Range: -3.4115

Max Act: 3.3513. Min Act: -0.1686

Data Index: 1448120 (Python Code)

Max Activating Token Index: 572

Text #5

Max Range: 3.4115. Min Range: -3.4115

Max Act: 3.3215. Min Act: -0.1471

Data Index: 164009 (C4 (Web Text))

Max Activating Token Index: 535

Text #6

Max Range: 3.4115. Min Range: -3.4115

Max Act: 3.3175. Min Act: -0.1471

Data Index: 1472851 (Python Code)

Max Activating Token Index: 975

Text #7

Max Range: 3.4115. Min Range: -3.4115

Max Act: 3.3110. Min Act: -0.1471

Data Index: 1646555 (Python Code)

Max Activating Token Index: 131

Text #8

Max Range: 3.4115. Min Range: -3.4115

Max Act: 3.2894. Min Act: -0.1471

Data Index: 1616365 (Python Code)

Max Activating Token Index: 534

Text #9

Max Range: 3.4115. Min Range: -3.4115

Max Act: 3.2955. Min Act: -0.1699

Data Index: 1236664 (C4 (Web Text))

Max Activating Token Index: 483

Text #10

Max Range: 3.4115. Min Range: -3.4115

Max Act: 3.2825. Min Act: -0.1649

Data Index: 1585763 (Python Code)

Max Activating Token Index: 493

Text #11

Max Range: 3.4115. Min Range: -3.4115

Max Act: 3.2731. Min Act: -0.1608

Data Index: 1091561 (C4 (Web Text))

Max Activating Token Index: 174

Text #12

Max Range: 3.4115. Min Range: -3.4115

Max Act: 3.2709. Min Act: -0.1471

Data Index: 770521 (C4 (Web Text))

Max Activating Token Index: 367

Text #13

Max Range: 3.4115. Min Range: -3.4115

Max Act: 3.2591. Min Act: -0.1471

Data Index: 1383381 (Python Code)

Max Activating Token Index: 868

Text #14

Max Range: 3.4115. Min Range: -3.4115

Max Act: 3.2529. Min Act: -0.1692

Data Index: 672964 (C4 (Web Text))

Max Activating Token Index: 474

Text #15

Max Range: 3.4115. Min Range: -3.4115

Max Act: 3.2353. Min Act: -0.1689

Data Index: 894829 (C4 (Web Text))

Max Activating Token Index: 541

Text #16

Max Range: 3.4115. Min Range: -3.4115

Max Act: 3.2541. Min Act: -0.1471

Data Index: 1228338 (C4 (Web Text))

Max Activating Token Index: 950

Text #17

Max Range: 3.4115. Min Range: -3.4115

Max Act: 3.2458. Min Act: -0.1700

Data Index: 328575 (C4 (Web Text))

Max Activating Token Index: 763

Text #18

Max Range: 3.4115. Min Range: -3.4115

Max Act: 3.2205. Min Act: -0.1700

Data Index: 383558 (C4 (Web Text))

Max Activating Token Index: 484

Text #19

Max Range: 3.4115. Min Range: -3.4115

Max Act: 3.2203. Min Act: -0.1699

Data Index: 1028488 (C4 (Web Text))

Max Activating Token Index: 343