Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 2991 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 2.1116. Min Range: -2.1116

Max Act: 2.1112. Min Act: -0.1700

Data Index: 639909 (Open Web Text)

Max Activating Token Index: 115

Text #1

Max Range: 2.1116. Min Range: -2.1116

Max Act: 2.1116. Min Act: -0.1700

Data Index: 6941612 (Open Web Text)

Max Activating Token Index: 936

Text #2

Max Range: 2.1116. Min Range: -2.1116

Max Act: 2.0755. Min Act: -0.1700

Data Index: 1312256 (Open Web Text)

Max Activating Token Index: 237

Text #3

Max Range: 2.1116. Min Range: -2.1116

Max Act: 2.0653. Min Act: -0.1700

Data Index: 3687590 (Open Web Text)

Max Activating Token Index: 950

Text #4

Max Range: 2.1116. Min Range: -2.1116

Max Act: 2.0577. Min Act: -0.1700

Data Index: 4441978 (Open Web Text)

Max Activating Token Index: 418

Text #5

Max Range: 2.1116. Min Range: -2.1116

Max Act: 2.0574. Min Act: -0.1700

Data Index: 6803340 (Open Web Text)

Max Activating Token Index: 684

Text #6

Max Range: 2.1116. Min Range: -2.1116

Max Act: 2.0042. Min Act: -0.1700

Data Index: 1282295 (Open Web Text)

Max Activating Token Index: 17

Text #7

Max Range: 2.1116. Min Range: -2.1116

Max Act: 2.0323. Min Act: -0.1700

Data Index: 4621055 (Open Web Text)

Max Activating Token Index: 604

Text #8

Max Range: 2.1116. Min Range: -2.1116

Max Act: 1.9804. Min Act: -0.1700

Data Index: 3325140 (Open Web Text)

Max Activating Token Index: 669

Text #9

Max Range: 2.1116. Min Range: -2.1116

Max Act: 1.9764. Min Act: -0.1700

Data Index: 8328907 (Open Web Text)

Max Activating Token Index: 501

Text #10

Max Range: 2.1116. Min Range: -2.1116

Max Act: 1.9873. Min Act: -0.1700

Data Index: 8380901 (Open Web Text)

Max Activating Token Index: 130

Text #11

Max Range: 2.1116. Min Range: -2.1116

Max Act: 1.9935. Min Act: -0.1700

Data Index: 2597690 (Open Web Text)

Max Activating Token Index: 632

Text #12

Max Range: 2.1116. Min Range: -2.1116

Max Act: 1.9703. Min Act: -0.1700

Data Index: 1126105 (Open Web Text)

Max Activating Token Index: 73

Text #13

Max Range: 2.1116. Min Range: -2.1116

Max Act: 1.9751. Min Act: -0.1700

Data Index: 2441925 (Open Web Text)

Max Activating Token Index: 171

Text #14

Max Range: 2.1116. Min Range: -2.1116

Max Act: 1.9727. Min Act: -0.1700

Data Index: 4436318 (Open Web Text)

Max Activating Token Index: 117

Text #15

Max Range: 2.1116. Min Range: -2.1116

Max Act: 1.9709. Min Act: -0.1700

Data Index: 982442 (Open Web Text)

Max Activating Token Index: 8

Text #16

Max Range: 2.1116. Min Range: -2.1116

Max Act: 1.9768. Min Act: -0.1700

Data Index: 4090016 (Open Web Text)

Max Activating Token Index: 256

Text #17

Max Range: 2.1116. Min Range: -2.1116

Max Act: 1.9682. Min Act: -0.1700

Data Index: 6577222 (Open Web Text)

Max Activating Token Index: 647

Text #18

Max Range: 2.1116. Min Range: -2.1116

Max Act: 1.9853. Min Act: -0.1700

Data Index: 34626 (Open Web Text)

Max Activating Token Index: 67

Text #19

Max Range: 2.1116. Min Range: -2.1116

Max Act: 1.9633. Min Act: -0.1700

Data Index: 3734390 (Open Web Text)

Max Activating Token Index: 191