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

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

Neuron 462 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: 3.8945. Min Range: -3.8945

Max Act: 3.8945. Min Act: -0.1700

Data Index: 472470 (C4 (Web Text))

Max Activating Token Index: 93

Text #1

Max Range: 3.8945. Min Range: -3.8945

Max Act: 3.8320. Min Act: -0.1700

Data Index: 1281145 (C4 (Web Text))

Max Activating Token Index: 255

Text #2

Max Range: 3.8945. Min Range: -3.8945

Max Act: 3.8320. Min Act: -0.1700

Data Index: 1354350 (C4 (Web Text))

Max Activating Token Index: 69

Text #3

Max Range: 3.8945. Min Range: -3.8945

Max Act: 3.8320. Min Act: -0.1700

Data Index: 445832 (C4 (Web Text))

Max Activating Token Index: 765

Text #4

Max Range: 3.8945. Min Range: -3.8945

Max Act: 3.8633. Min Act: -0.1700

Data Index: 1272720 (C4 (Web Text))

Max Activating Token Index: 430

Text #5

Max Range: 3.8945. Min Range: -3.8945

Max Act: 3.8320. Min Act: -0.1700

Data Index: 795642 (C4 (Web Text))

Max Activating Token Index: 319

Text #6

Max Range: 3.8945. Min Range: -3.8945

Max Act: 3.8007. Min Act: -0.1700

Data Index: 919707 (C4 (Web Text))

Max Activating Token Index: 224

Text #7

Max Range: 3.8945. Min Range: -3.8945

Max Act: 3.8007. Min Act: -0.1700

Data Index: 1039622 (C4 (Web Text))

Max Activating Token Index: 515

Text #8

Max Range: 3.8945. Min Range: -3.8945

Max Act: 3.8007. Min Act: -0.1700

Data Index: 818391 (C4 (Web Text))

Max Activating Token Index: 557

Text #9

Max Range: 3.8945. Min Range: -3.8945

Max Act: 3.7694. Min Act: -0.1700

Data Index: 200003 (C4 (Web Text))

Max Activating Token Index: 771

Text #10

Max Range: 3.8945. Min Range: -3.8945

Max Act: 3.7068. Min Act: -0.1700

Data Index: 432628 (C4 (Web Text))

Max Activating Token Index: 645

Text #11

Max Range: 3.8945. Min Range: -3.8945

Max Act: 3.7694. Min Act: -0.1700

Data Index: 439435 (C4 (Web Text))

Max Activating Token Index: 72

Text #12

Max Range: 3.8945. Min Range: -3.8945

Max Act: 3.7694. Min Act: -0.1700

Data Index: 92894 (C4 (Web Text))

Max Activating Token Index: 866

Text #13

Max Range: 3.8945. Min Range: -3.8945

Max Act: 3.7381. Min Act: -0.1700

Data Index: 1169609 (C4 (Web Text))

Max Activating Token Index: 864

Text #14

Max Range: 3.8945. Min Range: -3.8945

Max Act: 3.7694. Min Act: -0.1700

Data Index: 1243608 (C4 (Web Text))

Max Activating Token Index: 996

Text #15

Max Range: 3.8945. Min Range: -3.8945

Max Act: 3.8007. Min Act: -0.1700

Data Index: 161497 (C4 (Web Text))

Max Activating Token Index: 818

Text #16

Max Range: 3.8945. Min Range: -3.8945

Max Act: 3.7694. Min Act: -0.1700

Data Index: 1271913 (C4 (Web Text))

Max Activating Token Index: 763

Text #17

Max Range: 3.8945. Min Range: -3.8945

Max Act: 3.7694. Min Act: -0.1700

Data Index: 395095 (C4 (Web Text))

Max Activating Token Index: 835

Text #18

Max Range: 3.8945. Min Range: -3.8945

Max Act: 3.8007. Min Act: -0.1700

Data Index: 310131 (C4 (Web Text))

Max Activating Token Index: 255

Text #19

Max Range: 3.8945. Min Range: -3.8945

Max Act: 3.7381. Min Act: -0.1700

Data Index: 332024 (C4 (Web Text))

Max Activating Token Index: 338