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

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

Neuron 2001 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: 3.1758. Min Range: -3.1758

Max Act: 3.1758. Min Act: -0.1700

Data Index: 1106581 (C4 (Web Text))

Max Activating Token Index: 529

Text #1

Max Range: 3.1758. Min Range: -3.1758

Max Act: 3.0972. Min Act: -0.1700

Data Index: 515984 (C4 (Web Text))

Max Activating Token Index: 247

Text #2

Max Range: 3.1758. Min Range: -3.1758

Max Act: 3.0829. Min Act: -0.1700

Data Index: 1041047 (C4 (Web Text))

Max Activating Token Index: 213

Text #3

Max Range: 3.1758. Min Range: -3.1758

Max Act: 3.0422. Min Act: -0.1700

Data Index: 1133193 (C4 (Web Text))

Max Activating Token Index: 891

Text #4

Max Range: 3.1758. Min Range: -3.1758

Max Act: 3.0358. Min Act: -0.1700

Data Index: 654298 (C4 (Web Text))

Max Activating Token Index: 89

Text #5

Max Range: 3.1758. Min Range: -3.1758

Max Act: 3.0278. Min Act: -0.1700

Data Index: 1534369 (Python Code)

Max Activating Token Index: 300

Text #6

Max Range: 3.1758. Min Range: -3.1758

Max Act: 3.0335. Min Act: -0.1680

Data Index: 1377475 (Python Code)

Max Activating Token Index: 102

Text #7

Max Range: 3.1758. Min Range: -3.1758

Max Act: 3.0350. Min Act: -0.1700

Data Index: 895299 (C4 (Web Text))

Max Activating Token Index: 447

Text #8

Max Range: 3.1758. Min Range: -3.1758

Max Act: 3.0180. Min Act: -0.1700

Data Index: 1015345 (C4 (Web Text))

Max Activating Token Index: 16

Text #9

Max Range: 3.1758. Min Range: -3.1758

Max Act: 3.0194. Min Act: -0.1661

Data Index: 1625735 (Python Code)

Max Activating Token Index: 96

Text #10

Max Range: 3.1758. Min Range: -3.1758

Max Act: 3.0172. Min Act: -0.1700

Data Index: 1551333 (Python Code)

Max Activating Token Index: 84

Text #11

Max Range: 3.1758. Min Range: -3.1758

Max Act: 3.0054. Min Act: -0.1700

Data Index: 721071 (C4 (Web Text))

Max Activating Token Index: 29

Text #12

Max Range: 3.1758. Min Range: -3.1758

Max Act: 3.0004. Min Act: -0.1700

Data Index: 6915 (C4 (Web Text))

Max Activating Token Index: 962

Text #13

Max Range: 3.1758. Min Range: -3.1758

Max Act: 3.0005. Min Act: -0.1700

Data Index: 748983 (C4 (Web Text))

Max Activating Token Index: 14

Text #14

Max Range: 3.1758. Min Range: -3.1758

Max Act: 2.9930. Min Act: -0.1700

Data Index: 404256 (C4 (Web Text))

Max Activating Token Index: 985

Text #15

Max Range: 3.1758. Min Range: -3.1758

Max Act: 3.0002. Min Act: -0.1699

Data Index: 1656348 (Python Code)

Max Activating Token Index: 36

Text #16

Max Range: 3.1758. Min Range: -3.1758

Max Act: 2.9880. Min Act: -0.1700

Data Index: 876564 (C4 (Web Text))

Max Activating Token Index: 801

Text #17

Max Range: 3.1758. Min Range: -3.1758

Max Act: 3.0032. Min Act: -0.1700

Data Index: 379977 (C4 (Web Text))

Max Activating Token Index: 379

Text #18

Max Range: 3.1758. Min Range: -3.1758

Max Act: 3.0012. Min Act: -0.1700

Data Index: 435321 (C4 (Web Text))

Max Activating Token Index: 371

Text #19

Max Range: 3.1758. Min Range: -3.1758

Max Act: 2.9867. Min Act: -0.1689

Data Index: 1377098 (Python Code)

Max Activating Token Index: 563