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

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

Neuron 164 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: 5.0477. Min Range: -5.0477

Max Act: 5.0477. Min Act: -0.1700

Data Index: 1327510 (C4 (Web Text))

Max Activating Token Index: 345

Text #1

Max Range: 5.0477. Min Range: -5.0477

Max Act: 4.9852. Min Act: -0.1700

Data Index: 895058 (C4 (Web Text))

Max Activating Token Index: 457

Text #2

Max Range: 5.0477. Min Range: -5.0477

Max Act: 4.9540. Min Act: -0.1700

Data Index: 318112 (C4 (Web Text))

Max Activating Token Index: 134

Text #3

Max Range: 5.0477. Min Range: -5.0477

Max Act: 4.8602. Min Act: -0.1700

Data Index: 728237 (C4 (Web Text))

Max Activating Token Index: 119

Text #4

Max Range: 5.0477. Min Range: -5.0477

Max Act: 4.8602. Min Act: -0.1700

Data Index: 926728 (C4 (Web Text))

Max Activating Token Index: 710

Text #5

Max Range: 5.0477. Min Range: -5.0477

Max Act: 4.7977. Min Act: -0.1700

Data Index: 393101 (C4 (Web Text))

Max Activating Token Index: 786

Text #6

Max Range: 5.0477. Min Range: -5.0477

Max Act: 4.8290. Min Act: -0.1700

Data Index: 1108987 (C4 (Web Text))

Max Activating Token Index: 775

Text #7

Max Range: 5.0477. Min Range: -5.0477

Max Act: 4.7665. Min Act: -0.1700

Data Index: 812144 (C4 (Web Text))

Max Activating Token Index: 314

Text #8

Max Range: 5.0477. Min Range: -5.0477

Max Act: 4.7977. Min Act: -0.1700

Data Index: 1290462 (C4 (Web Text))

Max Activating Token Index: 516

Text #9

Max Range: 5.0477. Min Range: -5.0477

Max Act: 4.7977. Min Act: -0.1700

Data Index: 77329 (C4 (Web Text))

Max Activating Token Index: 202

Text #10

Max Range: 5.0477. Min Range: -5.0477

Max Act: 4.7665. Min Act: -0.1700

Data Index: 569109 (C4 (Web Text))

Max Activating Token Index: 45

Text #11

Max Range: 5.0477. Min Range: -5.0477

Max Act: 4.7665. Min Act: -0.1700

Data Index: 603098 (C4 (Web Text))

Max Activating Token Index: 963

Text #12

Max Range: 5.0477. Min Range: -5.0477

Max Act: 4.7352. Min Act: -0.1699

Data Index: 698927 (C4 (Web Text))

Max Activating Token Index: 151

Text #13

Max Range: 5.0477. Min Range: -5.0477

Max Act: 4.7665. Min Act: -0.1700

Data Index: 130529 (C4 (Web Text))

Max Activating Token Index: 825

Text #14

Max Range: 5.0477. Min Range: -5.0477

Max Act: 4.7040. Min Act: -0.1700

Data Index: 202890 (C4 (Web Text))

Max Activating Token Index: 703

Text #15

Max Range: 5.0477. Min Range: -5.0477

Max Act: 4.6727. Min Act: -0.1700

Data Index: 597443 (C4 (Web Text))

Max Activating Token Index: 745

Text #16

Max Range: 5.0477. Min Range: -5.0477

Max Act: 4.7040. Min Act: -0.1700

Data Index: 1242948 (C4 (Web Text))

Max Activating Token Index: 67

Text #17

Max Range: 5.0477. Min Range: -5.0477

Max Act: 4.6415. Min Act: -0.1700

Data Index: 247397 (C4 (Web Text))

Max Activating Token Index: 803

Text #18

Max Range: 5.0477. Min Range: -5.0477

Max Act: 4.7040. Min Act: -0.1700

Data Index: 682301 (C4 (Web Text))

Max Activating Token Index: 488

Text #19

Max Range: 5.0477. Min Range: -5.0477

Max Act: 4.6727. Min Act: -0.1700

Data Index: 366041 (C4 (Web Text))

Max Activating Token Index: 947