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

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

Neuron 868 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6883. Min Range: -3.6883

Max Act: 3.6883. Min Act: -0.1700

Data Index: 187457 (C4 (Web Text))

Max Activating Token Index: 6

Text #1

Max Range: 3.6883. Min Range: -3.6883

Max Act: 3.6100. Min Act: -0.1700

Data Index: 91119 (C4 (Web Text))

Max Activating Token Index: 759

Text #2

Max Range: 3.6883. Min Range: -3.6883

Max Act: 3.5631. Min Act: -0.1700

Data Index: 544390 (C4 (Web Text))

Max Activating Token Index: 265

Text #3

Max Range: 3.6883. Min Range: -3.6883

Max Act: 3.5944. Min Act: -0.1700

Data Index: 1258424 (C4 (Web Text))

Max Activating Token Index: 99

Text #4

Max Range: 3.6883. Min Range: -3.6883

Max Act: 3.5631. Min Act: -0.1700

Data Index: 1193494 (C4 (Web Text))

Max Activating Token Index: 375

Text #5

Max Range: 3.6883. Min Range: -3.6883

Max Act: 3.5474. Min Act: -0.1700

Data Index: 1551201 (Python Code)

Max Activating Token Index: 452

Text #6

Max Range: 3.6883. Min Range: -3.6883

Max Act: 3.5474. Min Act: -0.1700

Data Index: 80123 (C4 (Web Text))

Max Activating Token Index: 50

Text #7

Max Range: 3.6883. Min Range: -3.6883

Max Act: 3.5631. Min Act: -0.1700

Data Index: 470403 (C4 (Web Text))

Max Activating Token Index: 30

Text #8

Max Range: 3.6883. Min Range: -3.6883

Max Act: 3.5317. Min Act: -0.1700

Data Index: 18823 (C4 (Web Text))

Max Activating Token Index: 44

Text #9

Max Range: 3.6883. Min Range: -3.6883

Max Act: 3.5317. Min Act: -0.1700

Data Index: 1554395 (Python Code)

Max Activating Token Index: 20

Text #10

Max Range: 3.6883. Min Range: -3.6883

Max Act: 3.5161. Min Act: -0.1700

Data Index: 1528866 (Python Code)

Max Activating Token Index: 152

Text #11

Max Range: 3.6883. Min Range: -3.6883

Max Act: 3.5474. Min Act: -0.1700

Data Index: 1437061 (Python Code)

Max Activating Token Index: 811

Text #12

Max Range: 3.6883. Min Range: -3.6883

Max Act: 3.5161. Min Act: -0.1700

Data Index: 1202373 (C4 (Web Text))

Max Activating Token Index: 726

Text #13

Max Range: 3.6883. Min Range: -3.6883

Max Act: 3.5161. Min Act: -0.1700

Data Index: 735926 (C4 (Web Text))

Max Activating Token Index: 172

Text #14

Max Range: 3.6883. Min Range: -3.6883

Max Act: 3.5161. Min Act: -0.1700

Data Index: 233724 (C4 (Web Text))

Max Activating Token Index: 291

Text #15

Max Range: 3.6883. Min Range: -3.6883

Max Act: 3.5004. Min Act: -0.1700

Data Index: 1283108 (C4 (Web Text))

Max Activating Token Index: 102

Text #16

Max Range: 3.6883. Min Range: -3.6883

Max Act: 3.5161. Min Act: -0.1700

Data Index: 1126405 (C4 (Web Text))

Max Activating Token Index: 140

Text #17

Max Range: 3.6883. Min Range: -3.6883

Max Act: 3.5317. Min Act: -0.1700

Data Index: 502083 (C4 (Web Text))

Max Activating Token Index: 116

Text #18

Max Range: 3.6883. Min Range: -3.6883

Max Act: 3.5317. Min Act: -0.1700

Data Index: 531525 (C4 (Web Text))

Max Activating Token Index: 42

Text #19

Max Range: 3.6883. Min Range: -3.6883

Max Act: 3.5161. Min Act: -0.1700

Data Index: 318409 (C4 (Web Text))

Max Activating Token Index: 11