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

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

Neuron 944 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.7262. Min Range: -5.7262

Max Act: 5.7262. Min Act: -0.1700

Data Index: 1021893 (C4 (Web Text))

Max Activating Token Index: 579

Text #1

Max Range: 5.7262. Min Range: -5.7262

Max Act: 5.6637. Min Act: -0.1699

Data Index: 986767 (C4 (Web Text))

Max Activating Token Index: 860

Text #2

Max Range: 5.7262. Min Range: -5.7262

Max Act: 5.6012. Min Act: -0.1700

Data Index: 1092025 (C4 (Web Text))

Max Activating Token Index: 387

Text #3

Max Range: 5.7262. Min Range: -5.7262

Max Act: 5.5387. Min Act: -0.1700

Data Index: 250439 (C4 (Web Text))

Max Activating Token Index: 226

Text #4

Max Range: 5.7262. Min Range: -5.7262

Max Act: 5.5699. Min Act: -0.1700

Data Index: 1173651 (C4 (Web Text))

Max Activating Token Index: 274

Text #5

Max Range: 5.7262. Min Range: -5.7262

Max Act: 5.5387. Min Act: -0.1700

Data Index: 172163 (C4 (Web Text))

Max Activating Token Index: 909

Text #6

Max Range: 5.7262. Min Range: -5.7262

Max Act: 5.5699. Min Act: -0.1700

Data Index: 520421 (C4 (Web Text))

Max Activating Token Index: 433

Text #7

Max Range: 5.7262. Min Range: -5.7262

Max Act: 5.5387. Min Act: -0.1700

Data Index: 453735 (C4 (Web Text))

Max Activating Token Index: 684

Text #8

Max Range: 5.7262. Min Range: -5.7262

Max Act: 5.4762. Min Act: -0.1700

Data Index: 1317008 (C4 (Web Text))

Max Activating Token Index: 240

Text #9

Max Range: 5.7262. Min Range: -5.7262

Max Act: 5.4449. Min Act: -0.1700

Data Index: 1228126 (C4 (Web Text))

Max Activating Token Index: 108

Text #10

Max Range: 5.7262. Min Range: -5.7262

Max Act: 5.4449. Min Act: -0.1700

Data Index: 906789 (C4 (Web Text))

Max Activating Token Index: 564

Text #11

Max Range: 5.7262. Min Range: -5.7262

Max Act: 5.4762. Min Act: -0.1700

Data Index: 511542 (C4 (Web Text))

Max Activating Token Index: 816

Text #12

Max Range: 5.7262. Min Range: -5.7262

Max Act: 5.5074. Min Act: -0.1700

Data Index: 379728 (C4 (Web Text))

Max Activating Token Index: 405

Text #13

Max Range: 5.7262. Min Range: -5.7262

Max Act: 5.4137. Min Act: -0.1700

Data Index: 592798 (C4 (Web Text))

Max Activating Token Index: 191

Text #14

Max Range: 5.7262. Min Range: -5.7262

Max Act: 5.5387. Min Act: -0.1700

Data Index: 787084 (C4 (Web Text))

Max Activating Token Index: 123

Text #15

Max Range: 5.7262. Min Range: -5.7262

Max Act: 5.4449. Min Act: -0.1700

Data Index: 324868 (C4 (Web Text))

Max Activating Token Index: 554

Text #16

Max Range: 5.7262. Min Range: -5.7262

Max Act: 5.3199. Min Act: -0.1700

Data Index: 979607 (C4 (Web Text))

Max Activating Token Index: 199

Text #17

Max Range: 5.7262. Min Range: -5.7262

Max Act: 5.4137. Min Act: -0.1700

Data Index: 435618 (C4 (Web Text))

Max Activating Token Index: 716

Text #18

Max Range: 5.7262. Min Range: -5.7262

Max Act: 5.4137. Min Act: -0.1700

Data Index: 1019185 (C4 (Web Text))

Max Activating Token Index: 198

Text #19

Max Range: 5.7262. Min Range: -5.7262

Max Act: 5.3824. Min Act: -0.1700

Data Index: 369531 (C4 (Web Text))

Max Activating Token Index: 102