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

Dataset: Open Web Text

Neuron 326 in Layer 2

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: 4.0002. Min Range: -4.0002

Max Act: 3.9761. Min Act: -0.1700

Data Index: 7688242 (Open Web Text)

Max Activating Token Index: 667

Text #1

Max Range: 4.0002. Min Range: -4.0002

Max Act: 4.0002. Min Act: -0.1700

Data Index: 5902389 (Open Web Text)

Max Activating Token Index: 472

Text #2

Max Range: 4.0002. Min Range: -4.0002

Max Act: 3.9840. Min Act: -0.1700

Data Index: 6557414 (Open Web Text)

Max Activating Token Index: 88

Text #3

Max Range: 4.0002. Min Range: -4.0002

Max Act: 3.9354. Min Act: -0.1700

Data Index: 7674769 (Open Web Text)

Max Activating Token Index: 405

Text #4

Max Range: 4.0002. Min Range: -4.0002

Max Act: 3.9669. Min Act: -0.1700

Data Index: 6814949 (Open Web Text)

Max Activating Token Index: 436

Text #5

Max Range: 4.0002. Min Range: -4.0002

Max Act: 3.9189. Min Act: -0.1700

Data Index: 3098202 (Open Web Text)

Max Activating Token Index: 883

Text #6

Max Range: 4.0002. Min Range: -4.0002

Max Act: 3.9020. Min Act: -0.1700

Data Index: 5684321 (Open Web Text)

Max Activating Token Index: 914

Text #7

Max Range: 4.0002. Min Range: -4.0002

Max Act: 3.8927. Min Act: -0.1700

Data Index: 6652217 (Open Web Text)

Max Activating Token Index: 467

Text #8

Max Range: 4.0002. Min Range: -4.0002

Max Act: 3.8700. Min Act: -0.1700

Data Index: 1987890 (Open Web Text)

Max Activating Token Index: 399

Text #9

Max Range: 4.0002. Min Range: -4.0002

Max Act: 3.8874. Min Act: -0.1700

Data Index: 7297436 (Open Web Text)

Max Activating Token Index: 112

Text #10

Max Range: 4.0002. Min Range: -4.0002

Max Act: 3.8748. Min Act: -0.1700

Data Index: 451261 (Open Web Text)

Max Activating Token Index: 840

Text #11

Max Range: 4.0002. Min Range: -4.0002

Max Act: 3.9111. Min Act: -0.1700

Data Index: 3398273 (Open Web Text)

Max Activating Token Index: 468

Text #12

Max Range: 4.0002. Min Range: -4.0002

Max Act: 3.8633. Min Act: -0.1700

Data Index: 3360924 (Open Web Text)

Max Activating Token Index: 353

Text #13

Max Range: 4.0002. Min Range: -4.0002

Max Act: 3.9229. Min Act: -0.1700

Data Index: 3169115 (Open Web Text)

Max Activating Token Index: 983

Text #14

Max Range: 4.0002. Min Range: -4.0002

Max Act: 3.8755. Min Act: -0.1700

Data Index: 6048628 (Open Web Text)

Max Activating Token Index: 740

Text #15

Max Range: 4.0002. Min Range: -4.0002

Max Act: 3.8828. Min Act: -0.1700

Data Index: 3163884 (Open Web Text)

Max Activating Token Index: 119

Text #16

Max Range: 4.0002. Min Range: -4.0002

Max Act: 3.8668. Min Act: -0.1700

Data Index: 3123589 (Open Web Text)

Max Activating Token Index: 449

Text #17

Max Range: 4.0002. Min Range: -4.0002

Max Act: 3.8952. Min Act: -0.1700

Data Index: 5466053 (Open Web Text)

Max Activating Token Index: 759

Text #18

Max Range: 4.0002. Min Range: -4.0002

Max Act: 3.8977. Min Act: -0.1700

Data Index: 4435973 (Open Web Text)

Max Activating Token Index: 582

Text #19

Max Range: 4.0002. Min Range: -4.0002

Max Act: 3.8459. Min Act: -0.1700

Data Index: 2944174 (Open Web Text)

Max Activating Token Index: 810