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

Dataset: Open Web Text

Neuron 1691 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: 4.1226. Min Range: -4.1226

Max Act: 4.1226. Min Act: -0.1700

Data Index: 6853044 (Open Web Text)

Max Activating Token Index: 777

Text #1

Max Range: 4.1226. Min Range: -4.1226

Max Act: 4.0917. Min Act: -0.1700

Data Index: 7241018 (Open Web Text)

Max Activating Token Index: 572

Text #2

Max Range: 4.1226. Min Range: -4.1226

Max Act: 4.0950. Min Act: -0.1700

Data Index: 5741528 (Open Web Text)

Max Activating Token Index: 739

Text #3

Max Range: 4.1226. Min Range: -4.1226

Max Act: 4.0797. Min Act: -0.1700

Data Index: 3982268 (Open Web Text)

Max Activating Token Index: 121

Text #4

Max Range: 4.1226. Min Range: -4.1226

Max Act: 4.0399. Min Act: -0.1700

Data Index: 7845291 (Open Web Text)

Max Activating Token Index: 282

Text #5

Max Range: 4.1226. Min Range: -4.1226

Max Act: 4.0477. Min Act: -0.1700

Data Index: 4288405 (Open Web Text)

Max Activating Token Index: 199

Text #6

Max Range: 4.1226. Min Range: -4.1226

Max Act: 4.0340. Min Act: -0.1700

Data Index: 8196284 (Open Web Text)

Max Activating Token Index: 552

Text #7

Max Range: 4.1226. Min Range: -4.1226

Max Act: 4.0465. Min Act: -0.1700

Data Index: 5643940 (Open Web Text)

Max Activating Token Index: 514

Text #8

Max Range: 4.1226. Min Range: -4.1226

Max Act: 4.0393. Min Act: -0.1700

Data Index: 3001232 (Open Web Text)

Max Activating Token Index: 630

Text #9

Max Range: 4.1226. Min Range: -4.1226

Max Act: 4.0467. Min Act: -0.1700

Data Index: 2632648 (Open Web Text)

Max Activating Token Index: 351

Text #10

Max Range: 4.1226. Min Range: -4.1226

Max Act: 4.0456. Min Act: -0.1700

Data Index: 1569774 (Open Web Text)

Max Activating Token Index: 174

Text #11

Max Range: 4.1226. Min Range: -4.1226

Max Act: 4.0310. Min Act: -0.1700

Data Index: 6790986 (Open Web Text)

Max Activating Token Index: 510

Text #12

Max Range: 4.1226. Min Range: -4.1226

Max Act: 4.0476. Min Act: -0.1700

Data Index: 1482843 (Open Web Text)

Max Activating Token Index: 325

Text #13

Max Range: 4.1226. Min Range: -4.1226

Max Act: 3.9911. Min Act: -0.1700

Data Index: 2035287 (Open Web Text)

Max Activating Token Index: 614

Text #14

Max Range: 4.1226. Min Range: -4.1226

Max Act: 4.0367. Min Act: -0.1700

Data Index: 2195732 (Open Web Text)

Max Activating Token Index: 1010

Text #15

Max Range: 4.1226. Min Range: -4.1226

Max Act: 4.0110. Min Act: -0.1700

Data Index: 2155589 (Open Web Text)

Max Activating Token Index: 373

Text #16

Max Range: 4.1226. Min Range: -4.1226

Max Act: 4.0320. Min Act: -0.1700

Data Index: 8439076 (Open Web Text)

Max Activating Token Index: 226

Text #17

Max Range: 4.1226. Min Range: -4.1226

Max Act: 4.0234. Min Act: -0.1700

Data Index: 4822999 (Open Web Text)

Max Activating Token Index: 204

Text #18

Max Range: 4.1226. Min Range: -4.1226

Max Act: 4.0219. Min Act: -0.1700

Data Index: 4829423 (Open Web Text)

Max Activating Token Index: 989

Text #19

Max Range: 4.1226. Min Range: -4.1226

Max Act: 4.0087. Min Act: -0.1700

Data Index: 8485569 (Open Web Text)

Max Activating Token Index: 249