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

Dataset: Open Web Text

Neuron 1956 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: 1.9626. Min Range: -1.9626

Max Act: 1.9576. Min Act: -0.1700

Data Index: 2631845 (Open Web Text)

Max Activating Token Index: 198

Text #1

Max Range: 1.9626. Min Range: -1.9626

Max Act: 1.9626. Min Act: -0.1700

Data Index: 5058992 (Open Web Text)

Max Activating Token Index: 502

Text #2

Max Range: 1.9626. Min Range: -1.9626

Max Act: 1.9139. Min Act: -0.1700

Data Index: 3496786 (Open Web Text)

Max Activating Token Index: 181

Text #3

Max Range: 1.9626. Min Range: -1.9626

Max Act: 1.8946. Min Act: -0.1700

Data Index: 2158535 (Open Web Text)

Max Activating Token Index: 85

Text #4

Max Range: 1.9626. Min Range: -1.9626

Max Act: 1.9095. Min Act: -0.1700

Data Index: 4887244 (Open Web Text)

Max Activating Token Index: 69

Text #5

Max Range: 1.9626. Min Range: -1.9626

Max Act: 1.8861. Min Act: -0.1700

Data Index: 1798519 (Open Web Text)

Max Activating Token Index: 215

Text #6

Max Range: 1.9626. Min Range: -1.9626

Max Act: 1.8792. Min Act: -0.1700

Data Index: 8326683 (Open Web Text)

Max Activating Token Index: 399

Text #7

Max Range: 1.9626. Min Range: -1.9626

Max Act: 1.8887. Min Act: -0.1699

Data Index: 8614438 (Open Web Text)

Max Activating Token Index: 691

Text #8

Max Range: 1.9626. Min Range: -1.9626

Max Act: 1.8760. Min Act: -0.1700

Data Index: 2850990 (Open Web Text)

Max Activating Token Index: 147

Text #9

Max Range: 1.9626. Min Range: -1.9626

Max Act: 1.8769. Min Act: -0.1700

Data Index: 7512201 (Open Web Text)

Max Activating Token Index: 89

Text #10

Max Range: 1.9626. Min Range: -1.9626

Max Act: 1.8869. Min Act: -0.1700

Data Index: 7889880 (Open Web Text)

Max Activating Token Index: 591

Text #11

Max Range: 1.9626. Min Range: -1.9626

Max Act: 1.8888. Min Act: -0.1700

Data Index: 7760146 (Open Web Text)

Max Activating Token Index: 616

Text #12

Max Range: 1.9626. Min Range: -1.9626

Max Act: 1.8703. Min Act: -0.1700

Data Index: 7909238 (Open Web Text)

Max Activating Token Index: 353

Text #13

Max Range: 1.9626. Min Range: -1.9626

Max Act: 1.8626. Min Act: -0.1700

Data Index: 7510340 (Open Web Text)

Max Activating Token Index: 174

Text #14

Max Range: 1.9626. Min Range: -1.9626

Max Act: 1.8705. Min Act: -0.1700

Data Index: 5793180 (Open Web Text)

Max Activating Token Index: 625

Text #15

Max Range: 1.9626. Min Range: -1.9626

Max Act: 1.8661. Min Act: -0.1700

Data Index: 2404263 (Open Web Text)

Max Activating Token Index: 186

Text #16

Max Range: 1.9626. Min Range: -1.9626

Max Act: 1.8579. Min Act: -0.1700

Data Index: 1796753 (Open Web Text)

Max Activating Token Index: 168

Text #17

Max Range: 1.9626. Min Range: -1.9626

Max Act: 1.8580. Min Act: -0.1700

Data Index: 1079420 (Open Web Text)

Max Activating Token Index: 824

Text #18

Max Range: 1.9626. Min Range: -1.9626

Max Act: 1.8592. Min Act: -0.1700

Data Index: 4873193 (Open Web Text)

Max Activating Token Index: 448

Text #19

Max Range: 1.9626. Min Range: -1.9626

Max Act: 1.8604. Min Act: -0.1700

Data Index: 6463015 (Open Web Text)

Max Activating Token Index: 584