Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 318 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 5.0669. Min Range: -5.0669

Max Act: 5.0669. Min Act: -0.1700

Data Index: 406514 (C4 (Web Text))

Max Activating Token Index: 775

Text #1

Max Range: 5.0669. Min Range: -5.0669

Max Act: 4.8169. Min Act: -0.1700

Data Index: 750481 (C4 (Web Text))

Max Activating Token Index: 1017

Text #2

Max Range: 5.0669. Min Range: -5.0669

Max Act: 4.7544. Min Act: -0.1700

Data Index: 162309 (C4 (Web Text))

Max Activating Token Index: 1018

Text #3

Max Range: 5.0669. Min Range: -5.0669

Max Act: 4.5981. Min Act: -0.1700

Data Index: 688030 (C4 (Web Text))

Max Activating Token Index: 916

Text #4

Max Range: 5.0669. Min Range: -5.0669

Max Act: 4.6606. Min Act: -0.1700

Data Index: 36273 (C4 (Web Text))

Max Activating Token Index: 371

Text #5

Max Range: 5.0669. Min Range: -5.0669

Max Act: 4.5669. Min Act: -0.1700

Data Index: 485220 (C4 (Web Text))

Max Activating Token Index: 157

Text #6

Max Range: 5.0669. Min Range: -5.0669

Max Act: 4.5669. Min Act: -0.1700

Data Index: 640268 (C4 (Web Text))

Max Activating Token Index: 770

Text #7

Max Range: 5.0669. Min Range: -5.0669

Max Act: 4.5669. Min Act: -0.1700

Data Index: 329280 (C4 (Web Text))

Max Activating Token Index: 544

Text #8

Max Range: 5.0669. Min Range: -5.0669

Max Act: 4.5356. Min Act: -0.1700

Data Index: 1300923 (C4 (Web Text))

Max Activating Token Index: 772

Text #9

Max Range: 5.0669. Min Range: -5.0669

Max Act: 4.5669. Min Act: -0.1700

Data Index: 1177057 (C4 (Web Text))

Max Activating Token Index: 931

Text #10

Max Range: 5.0669. Min Range: -5.0669

Max Act: 4.5356. Min Act: -0.1700

Data Index: 843979 (C4 (Web Text))

Max Activating Token Index: 674

Text #11

Max Range: 5.0669. Min Range: -5.0669

Max Act: 4.5044. Min Act: -0.1700

Data Index: 996362 (C4 (Web Text))

Max Activating Token Index: 605

Text #12

Max Range: 5.0669. Min Range: -5.0669

Max Act: 4.5044. Min Act: -0.1700

Data Index: 987147 (C4 (Web Text))

Max Activating Token Index: 980

Text #13

Max Range: 5.0669. Min Range: -5.0669

Max Act: 4.5044. Min Act: -0.1700

Data Index: 1252758 (C4 (Web Text))

Max Activating Token Index: 561

Text #14

Max Range: 5.0669. Min Range: -5.0669

Max Act: 4.5356. Min Act: -0.1700

Data Index: 545892 (C4 (Web Text))

Max Activating Token Index: 961

Text #15

Max Range: 5.0669. Min Range: -5.0669

Max Act: 4.4731. Min Act: -0.1700

Data Index: 1027958 (C4 (Web Text))

Max Activating Token Index: 430

Text #16

Max Range: 5.0669. Min Range: -5.0669

Max Act: 4.5044. Min Act: -0.1700

Data Index: 125386 (C4 (Web Text))

Max Activating Token Index: 468

Text #17

Max Range: 5.0669. Min Range: -5.0669

Max Act: 4.5044. Min Act: -0.1700

Data Index: 922570 (C4 (Web Text))

Max Activating Token Index: 250

Text #18

Max Range: 5.0669. Min Range: -5.0669

Max Act: 4.4419. Min Act: -0.1700

Data Index: 861 (C4 (Web Text))

Max Activating Token Index: 534

Text #19

Max Range: 5.0669. Min Range: -5.0669

Max Act: 4.5356. Min Act: -0.1700

Data Index: 383393 (C4 (Web Text))

Max Activating Token Index: 1018