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

Dataset: Open Web Text

Neuron 628 in Layer 5

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: 5.0861. Min Range: -5.0861

Max Act: 5.0861. Min Act: -0.1700

Data Index: 296440 (Open Web Text)

Max Activating Token Index: 52

Text #1

Max Range: 5.0861. Min Range: -5.0861

Max Act: 4.9167. Min Act: -0.1700

Data Index: 2353520 (Open Web Text)

Max Activating Token Index: 759

Text #2

Max Range: 5.0861. Min Range: -5.0861

Max Act: 4.8843. Min Act: -0.1700

Data Index: 7580928 (Open Web Text)

Max Activating Token Index: 331

Text #3

Max Range: 5.0861. Min Range: -5.0861

Max Act: 4.9185. Min Act: -0.1700

Data Index: 4326753 (Open Web Text)

Max Activating Token Index: 719

Text #4

Max Range: 5.0861. Min Range: -5.0861

Max Act: 4.9298. Min Act: -0.1700

Data Index: 6401817 (Open Web Text)

Max Activating Token Index: 826

Text #5

Max Range: 5.0861. Min Range: -5.0861

Max Act: 4.9004. Min Act: -0.1700

Data Index: 3301423 (Open Web Text)

Max Activating Token Index: 888

Text #6

Max Range: 5.0861. Min Range: -5.0861

Max Act: 4.9133. Min Act: -0.1700

Data Index: 68390 (Open Web Text)

Max Activating Token Index: 846

Text #7

Max Range: 5.0861. Min Range: -5.0861

Max Act: 4.9382. Min Act: -0.1700

Data Index: 622960 (Open Web Text)

Max Activating Token Index: 1023

Text #8

Max Range: 5.0861. Min Range: -5.0861

Max Act: 4.9171. Min Act: -0.1700

Data Index: 1982453 (Open Web Text)

Max Activating Token Index: 359

Text #9

Max Range: 5.0861. Min Range: -5.0861

Max Act: 4.8771. Min Act: -0.1700

Data Index: 6673812 (Open Web Text)

Max Activating Token Index: 958

Text #10

Max Range: 5.0861. Min Range: -5.0861

Max Act: 4.8376. Min Act: -0.1700

Data Index: 1399863 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 5.0861. Min Range: -5.0861

Max Act: 4.8376. Min Act: -0.1700

Data Index: 7512716 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 5.0861. Min Range: -5.0861

Max Act: 4.8376. Min Act: -0.1700

Data Index: 3469186 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 5.0861. Min Range: -5.0861

Max Act: 4.8376. Min Act: -0.1700

Data Index: 6974602 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 5.0861. Min Range: -5.0861

Max Act: 4.8376. Min Act: -0.1700

Data Index: 618906 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 5.0861. Min Range: -5.0861

Max Act: 4.8376. Min Act: -0.1700

Data Index: 189025 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 5.0861. Min Range: -5.0861

Max Act: 4.8376. Min Act: -0.1700

Data Index: 6385065 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 5.0861. Min Range: -5.0861

Max Act: 4.8152. Min Act: -0.1700

Data Index: 5936363 (Open Web Text)

Max Activating Token Index: 875

Text #18

Max Range: 5.0861. Min Range: -5.0861

Max Act: 4.8376. Min Act: -0.1700

Data Index: 5911664 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 5.0861. Min Range: -5.0861

Max Act: 4.8199. Min Act: -0.1700

Data Index: 5715729 (Open Web Text)

Max Activating Token Index: 791