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

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

Neuron 171 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: 5.0759. Min Range: -5.0759

Max Act: 5.0759. Min Act: -0.1700

Data Index: 1552814 (Python Code)

Max Activating Token Index: 397

Text #1

Max Range: 5.0759. Min Range: -5.0759

Max Act: 4.9446. Min Act: -0.1700

Data Index: 651590 (C4 (Web Text))

Max Activating Token Index: 898

Text #2

Max Range: 5.0759. Min Range: -5.0759

Max Act: 4.8493. Min Act: -0.1700

Data Index: 928346 (C4 (Web Text))

Max Activating Token Index: 52

Text #3

Max Range: 5.0759. Min Range: -5.0759

Max Act: 4.7072. Min Act: -0.1700

Data Index: 1610162 (Python Code)

Max Activating Token Index: 868

Text #4

Max Range: 5.0759. Min Range: -5.0759

Max Act: 4.7092. Min Act: -0.1700

Data Index: 1467690 (Python Code)

Max Activating Token Index: 72

Text #5

Max Range: 5.0759. Min Range: -5.0759

Max Act: 4.6697. Min Act: -0.1700

Data Index: 138586 (C4 (Web Text))

Max Activating Token Index: 485

Text #6

Max Range: 5.0759. Min Range: -5.0759

Max Act: 4.5998. Min Act: -0.1700

Data Index: 403079 (C4 (Web Text))

Max Activating Token Index: 393

Text #7

Max Range: 5.0759. Min Range: -5.0759

Max Act: 4.5767. Min Act: -0.1700

Data Index: 1403007 (Python Code)

Max Activating Token Index: 917

Text #8

Max Range: 5.0759. Min Range: -5.0759

Max Act: 4.6141. Min Act: -0.1700

Data Index: 1503824 (Python Code)

Max Activating Token Index: 138

Text #9

Max Range: 5.0759. Min Range: -5.0759

Max Act: 4.5504. Min Act: -0.1700

Data Index: 1641978 (Python Code)

Max Activating Token Index: 181

Text #10

Max Range: 5.0759. Min Range: -5.0759

Max Act: 4.5593. Min Act: -0.1699

Data Index: 1629550 (Python Code)

Max Activating Token Index: 950

Text #11

Max Range: 5.0759. Min Range: -5.0759

Max Act: 4.4943. Min Act: -0.1700

Data Index: 1365292 (Python Code)

Max Activating Token Index: 34

Text #12

Max Range: 5.0759. Min Range: -5.0759

Max Act: 4.4840. Min Act: -0.1700

Data Index: 1527640 (Python Code)

Max Activating Token Index: 868

Text #13

Max Range: 5.0759. Min Range: -5.0759

Max Act: 4.4408. Min Act: -0.1700

Data Index: 1385687 (Python Code)

Max Activating Token Index: 401

Text #14

Max Range: 5.0759. Min Range: -5.0759

Max Act: 4.4349. Min Act: -0.1700

Data Index: 1422652 (Python Code)

Max Activating Token Index: 663

Text #15

Max Range: 5.0759. Min Range: -5.0759

Max Act: 4.3922. Min Act: -0.1700

Data Index: 51568 (C4 (Web Text))

Max Activating Token Index: 759

Text #16

Max Range: 5.0759. Min Range: -5.0759

Max Act: 4.4126. Min Act: -0.1697

Data Index: 1501988 (Python Code)

Max Activating Token Index: 257

Text #17

Max Range: 5.0759. Min Range: -5.0759

Max Act: 4.4125. Min Act: -0.1700

Data Index: 1475558 (Python Code)

Max Activating Token Index: 317

Text #18

Max Range: 5.0759. Min Range: -5.0759

Max Act: 4.4260. Min Act: -0.1700

Data Index: 1395006 (Python Code)

Max Activating Token Index: 1011

Text #19

Max Range: 5.0759. Min Range: -5.0759

Max Act: 4.3738. Min Act: -0.1700

Data Index: 1444780 (Python Code)

Max Activating Token Index: 386