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

Dataset: Open Web Text

Neuron 567 in Layer 4

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: 3.9013. Min Range: -3.9013

Max Act: 3.9013. Min Act: -0.1700

Data Index: 8069366 (Open Web Text)

Max Activating Token Index: 6

Text #1

Max Range: 3.9013. Min Range: -3.9013

Max Act: 3.8981. Min Act: -0.1700

Data Index: 3735483 (Open Web Text)

Max Activating Token Index: 186

Text #2

Max Range: 3.9013. Min Range: -3.9013

Max Act: 3.8526. Min Act: -0.1700

Data Index: 5629321 (Open Web Text)

Max Activating Token Index: 433

Text #3

Max Range: 3.9013. Min Range: -3.9013

Max Act: 3.8226. Min Act: -0.1700

Data Index: 841713 (Open Web Text)

Max Activating Token Index: 49

Text #4

Max Range: 3.9013. Min Range: -3.9013

Max Act: 3.7921. Min Act: -0.1700

Data Index: 6781682 (Open Web Text)

Max Activating Token Index: 623

Text #5

Max Range: 3.9013. Min Range: -3.9013

Max Act: 3.7522. Min Act: -0.1700

Data Index: 7675354 (Open Web Text)

Max Activating Token Index: 444

Text #6

Max Range: 3.9013. Min Range: -3.9013

Max Act: 3.7837. Min Act: -0.1700

Data Index: 8085554 (Open Web Text)

Max Activating Token Index: 8

Text #7

Max Range: 3.9013. Min Range: -3.9013

Max Act: 3.7386. Min Act: -0.1700

Data Index: 2307675 (Open Web Text)

Max Activating Token Index: 22

Text #8

Max Range: 3.9013. Min Range: -3.9013

Max Act: 3.7494. Min Act: -0.1700

Data Index: 3980361 (Open Web Text)

Max Activating Token Index: 185

Text #9

Max Range: 3.9013. Min Range: -3.9013

Max Act: 3.7455. Min Act: -0.1700

Data Index: 1254411 (Open Web Text)

Max Activating Token Index: 339

Text #10

Max Range: 3.9013. Min Range: -3.9013

Max Act: 3.7423. Min Act: -0.1700

Data Index: 433522 (Open Web Text)

Max Activating Token Index: 189

Text #11

Max Range: 3.9013. Min Range: -3.9013

Max Act: 3.7451. Min Act: -0.1700

Data Index: 3556403 (Open Web Text)

Max Activating Token Index: 117

Text #12

Max Range: 3.9013. Min Range: -3.9013

Max Act: 3.7582. Min Act: -0.1700

Data Index: 8426113 (Open Web Text)

Max Activating Token Index: 391

Text #13

Max Range: 3.9013. Min Range: -3.9013

Max Act: 3.7096. Min Act: -0.1700

Data Index: 263177 (Open Web Text)

Max Activating Token Index: 268

Text #14

Max Range: 3.9013. Min Range: -3.9013

Max Act: 3.7185. Min Act: -0.1700

Data Index: 8066229 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 3.9013. Min Range: -3.9013

Max Act: 3.7231. Min Act: -0.1700

Data Index: 8234515 (Open Web Text)

Max Activating Token Index: 300

Text #16

Max Range: 3.9013. Min Range: -3.9013

Max Act: 3.7232. Min Act: -0.1700

Data Index: 2697946 (Open Web Text)

Max Activating Token Index: 321

Text #17

Max Range: 3.9013. Min Range: -3.9013

Max Act: 3.6990. Min Act: -0.1700

Data Index: 3574152 (Open Web Text)

Max Activating Token Index: 139

Text #18

Max Range: 3.9013. Min Range: -3.9013

Max Act: 3.7303. Min Act: -0.1700

Data Index: 5890103 (Open Web Text)

Max Activating Token Index: 251

Text #19

Max Range: 3.9013. Min Range: -3.9013

Max Act: 3.6917. Min Act: -0.1700

Data Index: 1489626 (Open Web Text)

Max Activating Token Index: 658