Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 502 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.3485. Min Range: -3.3485

Max Act: 3.3485. Min Act: -0.1700

Data Index: 1339492 (C4 (Web Text))

Max Activating Token Index: 600

Text #1

Max Range: 3.3485. Min Range: -3.3485

Max Act: 3.3485. Min Act: -0.1700

Data Index: 240387 (C4 (Web Text))

Max Activating Token Index: 748

Text #2

Max Range: 3.3485. Min Range: -3.3485

Max Act: 3.3014. Min Act: -0.1700

Data Index: 227890 (C4 (Web Text))

Max Activating Token Index: 308

Text #3

Max Range: 3.3485. Min Range: -3.3485

Max Act: 3.2071. Min Act: -0.1700

Data Index: 538044 (C4 (Web Text))

Max Activating Token Index: 515

Text #4

Max Range: 3.3485. Min Range: -3.3485

Max Act: 3.2071. Min Act: -0.1700

Data Index: 996561 (C4 (Web Text))

Max Activating Token Index: 954

Text #5

Max Range: 3.3485. Min Range: -3.3485

Max Act: 3.1913. Min Act: -0.1700

Data Index: 1213841 (C4 (Web Text))

Max Activating Token Index: 820

Text #6

Max Range: 3.3485. Min Range: -3.3485

Max Act: 3.1598. Min Act: -0.1700

Data Index: 1176999 (C4 (Web Text))

Max Activating Token Index: 358

Text #7

Max Range: 3.3485. Min Range: -3.3485

Max Act: 3.1598. Min Act: -0.1700

Data Index: 1359297 (C4 (Web Text))

Max Activating Token Index: 472

Text #8

Max Range: 3.3485. Min Range: -3.3485

Max Act: 3.1913. Min Act: -0.1700

Data Index: 1026661 (C4 (Web Text))

Max Activating Token Index: 527

Text #9

Max Range: 3.3485. Min Range: -3.3485

Max Act: 3.1913. Min Act: -0.1700

Data Index: 1299346 (C4 (Web Text))

Max Activating Token Index: 199

Text #10

Max Range: 3.3485. Min Range: -3.3485

Max Act: 3.1598. Min Act: -0.1700

Data Index: 905598 (C4 (Web Text))

Max Activating Token Index: 449

Text #11

Max Range: 3.3485. Min Range: -3.3485

Max Act: 3.1126. Min Act: -0.1700

Data Index: 551649 (C4 (Web Text))

Max Activating Token Index: 633

Text #12

Max Range: 3.3485. Min Range: -3.3485

Max Act: 3.0968. Min Act: -0.1700

Data Index: 111702 (C4 (Web Text))

Max Activating Token Index: 396

Text #13

Max Range: 3.3485. Min Range: -3.3485

Max Act: 3.1441. Min Act: -0.1700

Data Index: 269774 (C4 (Web Text))

Max Activating Token Index: 149

Text #14

Max Range: 3.3485. Min Range: -3.3485

Max Act: 3.0810. Min Act: -0.1700

Data Index: 203543 (C4 (Web Text))

Max Activating Token Index: 186

Text #15

Max Range: 3.3485. Min Range: -3.3485

Max Act: 3.0968. Min Act: -0.1700

Data Index: 320356 (C4 (Web Text))

Max Activating Token Index: 882

Text #16

Max Range: 3.3485. Min Range: -3.3485

Max Act: 3.1126. Min Act: -0.1700

Data Index: 948016 (C4 (Web Text))

Max Activating Token Index: 158

Text #17

Max Range: 3.3485. Min Range: -3.3485

Max Act: 3.0968. Min Act: -0.1700

Data Index: 179847 (C4 (Web Text))

Max Activating Token Index: 136

Text #18

Max Range: 3.3485. Min Range: -3.3485

Max Act: 3.1126. Min Act: -0.1700

Data Index: 6869 (C4 (Web Text))

Max Activating Token Index: 863

Text #19

Max Range: 3.3485. Min Range: -3.3485

Max Act: 3.0968. Min Act: -0.1700

Data Index: 183090 (C4 (Web Text))

Max Activating Token Index: 437