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

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

Neuron 787 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: 4.3269. Min Range: -4.3269

Max Act: 4.3269. Min Act: -0.1700

Data Index: 1014522 (C4 (Web Text))

Max Activating Token Index: 230

Text #1

Max Range: 4.3269. Min Range: -4.3269

Max Act: 4.1706. Min Act: -0.1699

Data Index: 614559 (C4 (Web Text))

Max Activating Token Index: 143

Text #2

Max Range: 4.3269. Min Range: -4.3269

Max Act: 4.1706. Min Act: -0.1700

Data Index: 946992 (C4 (Web Text))

Max Activating Token Index: 919

Text #3

Max Range: 4.3269. Min Range: -4.3269

Max Act: 4.1394. Min Act: -0.1700

Data Index: 8571 (C4 (Web Text))

Max Activating Token Index: 615

Text #4

Max Range: 4.3269. Min Range: -4.3269

Max Act: 4.0768. Min Act: -0.1700

Data Index: 281351 (C4 (Web Text))

Max Activating Token Index: 267

Text #5

Max Range: 4.3269. Min Range: -4.3269

Max Act: 4.0768. Min Act: -0.1700

Data Index: 1151943 (C4 (Web Text))

Max Activating Token Index: 1002

Text #6

Max Range: 4.3269. Min Range: -4.3269

Max Act: 4.0456. Min Act: -0.1699

Data Index: 761924 (C4 (Web Text))

Max Activating Token Index: 205

Text #7

Max Range: 4.3269. Min Range: -4.3269

Max Act: 4.0143. Min Act: -0.1700

Data Index: 599217 (C4 (Web Text))

Max Activating Token Index: 841

Text #8

Max Range: 4.3269. Min Range: -4.3269

Max Act: 4.0768. Min Act: -0.1699

Data Index: 309705 (C4 (Web Text))

Max Activating Token Index: 318

Text #9

Max Range: 4.3269. Min Range: -4.3269

Max Act: 4.0143. Min Act: -0.1700

Data Index: 418102 (C4 (Web Text))

Max Activating Token Index: 153

Text #10

Max Range: 4.3269. Min Range: -4.3269

Max Act: 3.9830. Min Act: -0.1700

Data Index: 948286 (C4 (Web Text))

Max Activating Token Index: 177

Text #11

Max Range: 4.3269. Min Range: -4.3269

Max Act: 3.9830. Min Act: -0.1700

Data Index: 280110 (C4 (Web Text))

Max Activating Token Index: 71

Text #12

Max Range: 4.3269. Min Range: -4.3269

Max Act: 3.9830. Min Act: -0.1700

Data Index: 1125354 (C4 (Web Text))

Max Activating Token Index: 133

Text #13

Max Range: 4.3269. Min Range: -4.3269

Max Act: 3.9830. Min Act: -0.1700

Data Index: 1117664 (C4 (Web Text))

Max Activating Token Index: 93

Text #14

Max Range: 4.3269. Min Range: -4.3269

Max Act: 3.9830. Min Act: -0.1700

Data Index: 350767 (C4 (Web Text))

Max Activating Token Index: 183

Text #15

Max Range: 4.3269. Min Range: -4.3269

Max Act: 3.9830. Min Act: -0.1699

Data Index: 1240706 (C4 (Web Text))

Max Activating Token Index: 268

Text #16

Max Range: 4.3269. Min Range: -4.3269

Max Act: 3.9830. Min Act: -0.1700

Data Index: 1287478 (C4 (Web Text))

Max Activating Token Index: 107

Text #17

Max Range: 4.3269. Min Range: -4.3269

Max Act: 3.9205. Min Act: -0.1700

Data Index: 43717 (C4 (Web Text))

Max Activating Token Index: 811

Text #18

Max Range: 4.3269. Min Range: -4.3269

Max Act: 3.9830. Min Act: -0.1700

Data Index: 1280777 (C4 (Web Text))

Max Activating Token Index: 794

Text #19

Max Range: 4.3269. Min Range: -4.3269

Max Act: 3.9518. Min Act: -0.1700

Data Index: 1106459 (C4 (Web Text))

Max Activating Token Index: 517