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

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

Neuron 811 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7755. Min Range: -3.7755

Max Act: 3.7755. Min Act: -0.1700

Data Index: 884046 (C4 (Web Text))

Max Activating Token Index: 961

Text #1

Max Range: 3.7755. Min Range: -3.7755

Max Act: 3.7442. Min Act: -0.1700

Data Index: 833533 (C4 (Web Text))

Max Activating Token Index: 49

Text #2

Max Range: 3.7755. Min Range: -3.7755

Max Act: 3.7129. Min Act: -0.1700

Data Index: 976214 (C4 (Web Text))

Max Activating Token Index: 353

Text #3

Max Range: 3.7755. Min Range: -3.7755

Max Act: 3.7129. Min Act: -0.1700

Data Index: 553958 (C4 (Web Text))

Max Activating Token Index: 213

Text #4

Max Range: 3.7755. Min Range: -3.7755

Max Act: 3.6816. Min Act: -0.1700

Data Index: 1341577 (C4 (Web Text))

Max Activating Token Index: 372

Text #5

Max Range: 3.7755. Min Range: -3.7755

Max Act: 3.6816. Min Act: -0.1700

Data Index: 834776 (C4 (Web Text))

Max Activating Token Index: 811

Text #6

Max Range: 3.7755. Min Range: -3.7755

Max Act: 3.6503. Min Act: -0.1700

Data Index: 131475 (C4 (Web Text))

Max Activating Token Index: 443

Text #7

Max Range: 3.7755. Min Range: -3.7755

Max Act: 3.6816. Min Act: -0.1700

Data Index: 410427 (C4 (Web Text))

Max Activating Token Index: 538

Text #8

Max Range: 3.7755. Min Range: -3.7755

Max Act: 3.6816. Min Act: -0.1700

Data Index: 126821 (C4 (Web Text))

Max Activating Token Index: 791

Text #9

Max Range: 3.7755. Min Range: -3.7755

Max Act: 3.6816. Min Act: -0.1700

Data Index: 190198 (C4 (Web Text))

Max Activating Token Index: 811

Text #10

Max Range: 3.7755. Min Range: -3.7755

Max Act: 3.6816. Min Act: -0.1700

Data Index: 236103 (C4 (Web Text))

Max Activating Token Index: 265

Text #11

Max Range: 3.7755. Min Range: -3.7755

Max Act: 3.6816. Min Act: -0.1700

Data Index: 433252 (C4 (Web Text))

Max Activating Token Index: 653

Text #12

Max Range: 3.7755. Min Range: -3.7755

Max Act: 3.6503. Min Act: -0.1700

Data Index: 359686 (C4 (Web Text))

Max Activating Token Index: 510

Text #13

Max Range: 3.7755. Min Range: -3.7755

Max Act: 3.6816. Min Act: -0.1700

Data Index: 534117 (C4 (Web Text))

Max Activating Token Index: 39

Text #14

Max Range: 3.7755. Min Range: -3.7755

Max Act: 3.6816. Min Act: -0.1700

Data Index: 1066980 (C4 (Web Text))

Max Activating Token Index: 560

Text #15

Max Range: 3.7755. Min Range: -3.7755

Max Act: 3.6190. Min Act: -0.1700

Data Index: 380658 (C4 (Web Text))

Max Activating Token Index: 201

Text #16

Max Range: 3.7755. Min Range: -3.7755

Max Act: 3.6503. Min Act: -0.1700

Data Index: 486648 (C4 (Web Text))

Max Activating Token Index: 67

Text #17

Max Range: 3.7755. Min Range: -3.7755

Max Act: 3.6503. Min Act: -0.1700

Data Index: 486423 (C4 (Web Text))

Max Activating Token Index: 418

Text #18

Max Range: 3.7755. Min Range: -3.7755

Max Act: 3.6503. Min Act: -0.1700

Data Index: 800413 (C4 (Web Text))

Max Activating Token Index: 760

Text #19

Max Range: 3.7755. Min Range: -3.7755

Max Act: 3.6190. Min Act: -0.1700

Data Index: 874682 (C4 (Web Text))

Max Activating Token Index: 779