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

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

Neuron 741 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: 3.6852. Min Range: -3.6852

Max Act: 3.6852. Min Act: -0.1700

Data Index: 479568 (C4 (Web Text))

Max Activating Token Index: 184

Text #1

Max Range: 3.6852. Min Range: -3.6852

Max Act: 3.6047. Min Act: -0.1699

Data Index: 333653 (C4 (Web Text))

Max Activating Token Index: 296

Text #2

Max Range: 3.6852. Min Range: -3.6852

Max Act: 3.6187. Min Act: -0.1700

Data Index: 580535 (C4 (Web Text))

Max Activating Token Index: 526

Text #3

Max Range: 3.6852. Min Range: -3.6852

Max Act: 3.5720. Min Act: -0.1698

Data Index: 1490682 (Python Code)

Max Activating Token Index: 434

Text #4

Max Range: 3.6852. Min Range: -3.6852

Max Act: 3.5668. Min Act: -0.1699

Data Index: 1429479 (Python Code)

Max Activating Token Index: 788

Text #5

Max Range: 3.6852. Min Range: -3.6852

Max Act: 3.5790. Min Act: -0.1699

Data Index: 852142 (C4 (Web Text))

Max Activating Token Index: 1012

Text #6

Max Range: 3.6852. Min Range: -3.6852

Max Act: 3.5787. Min Act: -0.1700

Data Index: 861421 (C4 (Web Text))

Max Activating Token Index: 730

Text #7

Max Range: 3.6852. Min Range: -3.6852

Max Act: 3.5242. Min Act: -0.1700

Data Index: 1190617 (C4 (Web Text))

Max Activating Token Index: 633

Text #8

Max Range: 3.6852. Min Range: -3.6852

Max Act: 3.5275. Min Act: -0.1699

Data Index: 1533318 (Python Code)

Max Activating Token Index: 691

Text #9

Max Range: 3.6852. Min Range: -3.6852

Max Act: 3.5492. Min Act: -0.1700

Data Index: 1581339 (Python Code)

Max Activating Token Index: 343

Text #10

Max Range: 3.6852. Min Range: -3.6852

Max Act: 3.5371. Min Act: -0.1697

Data Index: 951935 (C4 (Web Text))

Max Activating Token Index: 902

Text #11

Max Range: 3.6852. Min Range: -3.6852

Max Act: 3.4979. Min Act: -0.1700

Data Index: 1467948 (Python Code)

Max Activating Token Index: 857

Text #12

Max Range: 3.6852. Min Range: -3.6852

Max Act: 3.5160. Min Act: -0.1697

Data Index: 292526 (C4 (Web Text))

Max Activating Token Index: 887

Text #13

Max Range: 3.6852. Min Range: -3.6852

Max Act: 3.4693. Min Act: -0.1700

Data Index: 1058297 (C4 (Web Text))

Max Activating Token Index: 628

Text #14

Max Range: 3.6852. Min Range: -3.6852

Max Act: 3.4799. Min Act: -0.1700

Data Index: 1481515 (Python Code)

Max Activating Token Index: 868

Text #15

Max Range: 3.6852. Min Range: -3.6852

Max Act: 3.4616. Min Act: -0.1700

Data Index: 1643255 (Python Code)

Max Activating Token Index: 414

Text #16

Max Range: 3.6852. Min Range: -3.6852

Max Act: 3.4799. Min Act: -0.1699

Data Index: 1424915 (Python Code)

Max Activating Token Index: 538

Text #17

Max Range: 3.6852. Min Range: -3.6852

Max Act: 3.4770. Min Act: -0.1657

Data Index: 1502496 (Python Code)

Max Activating Token Index: 441

Text #18

Max Range: 3.6852. Min Range: -3.6852

Max Act: 3.4841. Min Act: -0.1700

Data Index: 382102 (C4 (Web Text))

Max Activating Token Index: 832

Text #19

Max Range: 3.6852. Min Range: -3.6852

Max Act: 3.4797. Min Act: -0.1700

Data Index: 513437 (C4 (Web Text))

Max Activating Token Index: 564