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

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

Neuron 238 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: 5.1936. Min Range: -5.1936

Max Act: 5.1936. Min Act: -0.1700

Data Index: 1002355 (C4 (Web Text))

Max Activating Token Index: 95

Text #1

Max Range: 5.1936. Min Range: -5.1936

Max Act: 5.0686. Min Act: -0.1700

Data Index: 998286 (C4 (Web Text))

Max Activating Token Index: 58

Text #2

Max Range: 5.1936. Min Range: -5.1936

Max Act: 5.0374. Min Act: -0.1700

Data Index: 1173222 (C4 (Web Text))

Max Activating Token Index: 155

Text #3

Max Range: 5.1936. Min Range: -5.1936

Max Act: 4.9436. Min Act: -0.1700

Data Index: 409424 (C4 (Web Text))

Max Activating Token Index: 620

Text #4

Max Range: 5.1936. Min Range: -5.1936

Max Act: 4.9124. Min Act: -0.1700

Data Index: 604422 (C4 (Web Text))

Max Activating Token Index: 200

Text #5

Max Range: 5.1936. Min Range: -5.1936

Max Act: 4.8499. Min Act: -0.1700

Data Index: 758938 (C4 (Web Text))

Max Activating Token Index: 98

Text #6

Max Range: 5.1936. Min Range: -5.1936

Max Act: 4.9436. Min Act: -0.1700

Data Index: 67425 (C4 (Web Text))

Max Activating Token Index: 69

Text #7

Max Range: 5.1936. Min Range: -5.1936

Max Act: 4.8811. Min Act: -0.1700

Data Index: 1034376 (C4 (Web Text))

Max Activating Token Index: 820

Text #8

Max Range: 5.1936. Min Range: -5.1936

Max Act: 4.9436. Min Act: -0.1700

Data Index: 1232792 (C4 (Web Text))

Max Activating Token Index: 93

Text #9

Max Range: 5.1936. Min Range: -5.1936

Max Act: 4.8499. Min Act: -0.1700

Data Index: 215201 (C4 (Web Text))

Max Activating Token Index: 548

Text #10

Max Range: 5.1936. Min Range: -5.1936

Max Act: 4.8811. Min Act: -0.1700

Data Index: 271875 (C4 (Web Text))

Max Activating Token Index: 158

Text #11

Max Range: 5.1936. Min Range: -5.1936

Max Act: 4.8811. Min Act: -0.1700

Data Index: 824450 (C4 (Web Text))

Max Activating Token Index: 143

Text #12

Max Range: 5.1936. Min Range: -5.1936

Max Act: 4.8811. Min Act: -0.1700

Data Index: 1121763 (C4 (Web Text))

Max Activating Token Index: 518

Text #13

Max Range: 5.1936. Min Range: -5.1936

Max Act: 4.8811. Min Act: -0.1700

Data Index: 847905 (C4 (Web Text))

Max Activating Token Index: 172

Text #14

Max Range: 5.1936. Min Range: -5.1936

Max Act: 4.9124. Min Act: -0.1700

Data Index: 1194202 (C4 (Web Text))

Max Activating Token Index: 132

Text #15

Max Range: 5.1936. Min Range: -5.1936

Max Act: 4.8811. Min Act: -0.1700

Data Index: 952672 (C4 (Web Text))

Max Activating Token Index: 53

Text #16

Max Range: 5.1936. Min Range: -5.1936

Max Act: 4.8499. Min Act: -0.1700

Data Index: 80337 (C4 (Web Text))

Max Activating Token Index: 70

Text #17

Max Range: 5.1936. Min Range: -5.1936

Max Act: 4.8811. Min Act: -0.1700

Data Index: 250324 (C4 (Web Text))

Max Activating Token Index: 57

Text #18

Max Range: 5.1936. Min Range: -5.1936

Max Act: 4.8811. Min Act: -0.1700

Data Index: 1111757 (C4 (Web Text))

Max Activating Token Index: 80

Text #19

Max Range: 5.1936. Min Range: -5.1936

Max Act: 4.8499. Min Act: -0.1700

Data Index: 1120478 (C4 (Web Text))

Max Activating Token Index: 883