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

Dataset: Open Web Text

Neuron 775 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: 3.9259. Min Range: -3.9259

Max Act: 3.9160. Min Act: -0.1700

Data Index: 1120542 (Open Web Text)

Max Activating Token Index: 512

Text #1

Max Range: 3.9259. Min Range: -3.9259

Max Act: 3.9259. Min Act: -0.1700

Data Index: 4584692 (Open Web Text)

Max Activating Token Index: 409

Text #2

Max Range: 3.9259. Min Range: -3.9259

Max Act: 3.9031. Min Act: -0.1700

Data Index: 5739949 (Open Web Text)

Max Activating Token Index: 372

Text #3

Max Range: 3.9259. Min Range: -3.9259

Max Act: 3.9113. Min Act: -0.1700

Data Index: 2899347 (Open Web Text)

Max Activating Token Index: 293

Text #4

Max Range: 3.9259. Min Range: -3.9259

Max Act: 3.8716. Min Act: -0.1700

Data Index: 791249 (Open Web Text)

Max Activating Token Index: 602

Text #5

Max Range: 3.9259. Min Range: -3.9259

Max Act: 3.8756. Min Act: -0.1700

Data Index: 5533574 (Open Web Text)

Max Activating Token Index: 387

Text #6

Max Range: 3.9259. Min Range: -3.9259

Max Act: 3.8598. Min Act: -0.1700

Data Index: 2215241 (Open Web Text)

Max Activating Token Index: 176

Text #7

Max Range: 3.9259. Min Range: -3.9259

Max Act: 3.8569. Min Act: -0.1700

Data Index: 6845500 (Open Web Text)

Max Activating Token Index: 891

Text #8

Max Range: 3.9259. Min Range: -3.9259

Max Act: 3.8899. Min Act: -0.1700

Data Index: 3817901 (Open Web Text)

Max Activating Token Index: 698

Text #9

Max Range: 3.9259. Min Range: -3.9259

Max Act: 3.8579. Min Act: -0.1700

Data Index: 8027230 (Open Web Text)

Max Activating Token Index: 317

Text #10

Max Range: 3.9259. Min Range: -3.9259

Max Act: 3.8237. Min Act: -0.1700

Data Index: 1572197 (Open Web Text)

Max Activating Token Index: 294

Text #11

Max Range: 3.9259. Min Range: -3.9259

Max Act: 3.8273. Min Act: -0.1700

Data Index: 2849500 (Open Web Text)

Max Activating Token Index: 432

Text #12

Max Range: 3.9259. Min Range: -3.9259

Max Act: 3.8523. Min Act: -0.1700

Data Index: 8637101 (Open Web Text)

Max Activating Token Index: 184

Text #13

Max Range: 3.9259. Min Range: -3.9259

Max Act: 3.8391. Min Act: -0.1700

Data Index: 4707570 (Open Web Text)

Max Activating Token Index: 391

Text #14

Max Range: 3.9259. Min Range: -3.9259

Max Act: 3.8519. Min Act: -0.1700

Data Index: 3737920 (Open Web Text)

Max Activating Token Index: 882

Text #15

Max Range: 3.9259. Min Range: -3.9259

Max Act: 3.8351. Min Act: -0.1700

Data Index: 5775828 (Open Web Text)

Max Activating Token Index: 224

Text #16

Max Range: 3.9259. Min Range: -3.9259

Max Act: 3.8023. Min Act: -0.1700

Data Index: 4375383 (Open Web Text)

Max Activating Token Index: 581

Text #17

Max Range: 3.9259. Min Range: -3.9259

Max Act: 3.7869. Min Act: -0.1700

Data Index: 4386921 (Open Web Text)

Max Activating Token Index: 201

Text #18

Max Range: 3.9259. Min Range: -3.9259

Max Act: 3.8073. Min Act: -0.1700

Data Index: 4624197 (Open Web Text)

Max Activating Token Index: 582

Text #19

Max Range: 3.9259. Min Range: -3.9259

Max Act: 3.8018. Min Act: -0.1700

Data Index: 1057346 (Open Web Text)

Max Activating Token Index: 645