Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 482 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.7754. Min Range: -3.7754

Max Act: 3.7754. Min Act: -0.1700

Data Index: 1434792 (Python Code)

Max Activating Token Index: 186

Text #1

Max Range: 3.7754. Min Range: -3.7754

Max Act: 3.7754. Min Act: -0.1700

Data Index: 1266796 (C4 (Web Text))

Max Activating Token Index: 349

Text #2

Max Range: 3.7754. Min Range: -3.7754

Max Act: 3.6972. Min Act: -0.1700

Data Index: 1578627 (Python Code)

Max Activating Token Index: 412

Text #3

Max Range: 3.7754. Min Range: -3.7754

Max Act: 3.7128. Min Act: -0.1700

Data Index: 1465859 (Python Code)

Max Activating Token Index: 195

Text #4

Max Range: 3.7754. Min Range: -3.7754

Max Act: 3.5876. Min Act: -0.1700

Data Index: 1494453 (Python Code)

Max Activating Token Index: 875

Text #5

Max Range: 3.7754. Min Range: -3.7754

Max Act: 3.5563. Min Act: -0.1700

Data Index: 1538603 (Python Code)

Max Activating Token Index: 104

Text #6

Max Range: 3.7754. Min Range: -3.7754

Max Act: 3.5876. Min Act: -0.1700

Data Index: 514579 (C4 (Web Text))

Max Activating Token Index: 947

Text #7

Max Range: 3.7754. Min Range: -3.7754

Max Act: 3.5563. Min Act: -0.1700

Data Index: 1622139 (Python Code)

Max Activating Token Index: 914

Text #8

Max Range: 3.7754. Min Range: -3.7754

Max Act: 3.5563. Min Act: -0.1700

Data Index: 1494415 (Python Code)

Max Activating Token Index: 855

Text #9

Max Range: 3.7754. Min Range: -3.7754

Max Act: 3.5406. Min Act: -0.1700

Data Index: 747429 (C4 (Web Text))

Max Activating Token Index: 352

Text #10

Max Range: 3.7754. Min Range: -3.7754

Max Act: 3.5093. Min Act: -0.1700

Data Index: 1614016 (Python Code)

Max Activating Token Index: 292

Text #11

Max Range: 3.7754. Min Range: -3.7754

Max Act: 3.5093. Min Act: -0.1700

Data Index: 352120 (C4 (Web Text))

Max Activating Token Index: 921

Text #12

Max Range: 3.7754. Min Range: -3.7754

Max Act: 3.5093. Min Act: -0.1700

Data Index: 914761 (C4 (Web Text))

Max Activating Token Index: 220

Text #13

Max Range: 3.7754. Min Range: -3.7754

Max Act: 3.5093. Min Act: -0.1700

Data Index: 1654083 (Python Code)

Max Activating Token Index: 184

Text #14

Max Range: 3.7754. Min Range: -3.7754

Max Act: 3.5250. Min Act: -0.1700

Data Index: 1553222 (Python Code)

Max Activating Token Index: 142

Text #15

Max Range: 3.7754. Min Range: -3.7754

Max Act: 3.4936. Min Act: -0.1700

Data Index: 1633864 (Python Code)

Max Activating Token Index: 734

Text #16

Max Range: 3.7754. Min Range: -3.7754

Max Act: 3.5093. Min Act: -0.1700

Data Index: 778210 (C4 (Web Text))

Max Activating Token Index: 721

Text #17

Max Range: 3.7754. Min Range: -3.7754

Max Act: 3.4466. Min Act: -0.1700

Data Index: 1380561 (Python Code)

Max Activating Token Index: 156

Text #18

Max Range: 3.7754. Min Range: -3.7754

Max Act: 3.4779. Min Act: -0.1700

Data Index: 1437069 (Python Code)

Max Activating Token Index: 458

Text #19

Max Range: 3.7754. Min Range: -3.7754

Max Act: 3.4623. Min Act: -0.1700

Data Index: 1419940 (Python Code)

Max Activating Token Index: 167