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

Dataset: Open Web Text

Neuron 2439 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: 1.8392. Min Range: -1.8392

Max Act: 1.8392. Min Act: -0.1700

Data Index: 61510 (Open Web Text)

Max Activating Token Index: 540

Text #1

Max Range: 1.8392. Min Range: -1.8392

Max Act: 1.8142. Min Act: -0.1699

Data Index: 8496752 (Open Web Text)

Max Activating Token Index: 102

Text #2

Max Range: 1.8392. Min Range: -1.8392

Max Act: 1.7872. Min Act: -0.1700

Data Index: 8804038 (Open Web Text)

Max Activating Token Index: 47

Text #3

Max Range: 1.8392. Min Range: -1.8392

Max Act: 1.7865. Min Act: -0.1700

Data Index: 1627748 (Open Web Text)

Max Activating Token Index: 579

Text #4

Max Range: 1.8392. Min Range: -1.8392

Max Act: 1.7627. Min Act: -0.1700

Data Index: 2031270 (Open Web Text)

Max Activating Token Index: 411

Text #5

Max Range: 1.8392. Min Range: -1.8392

Max Act: 1.7663. Min Act: -0.1700

Data Index: 3090159 (Open Web Text)

Max Activating Token Index: 501

Text #6

Max Range: 1.8392. Min Range: -1.8392

Max Act: 1.7647. Min Act: -0.1700

Data Index: 6019750 (Open Web Text)

Max Activating Token Index: 707

Text #7

Max Range: 1.8392. Min Range: -1.8392

Max Act: 1.7524. Min Act: -0.1700

Data Index: 7423768 (Open Web Text)

Max Activating Token Index: 396

Text #8

Max Range: 1.8392. Min Range: -1.8392

Max Act: 1.7564. Min Act: -0.1700

Data Index: 4894944 (Open Web Text)

Max Activating Token Index: 344

Text #9

Max Range: 1.8392. Min Range: -1.8392

Max Act: 1.7435. Min Act: -0.1700

Data Index: 1961716 (Open Web Text)

Max Activating Token Index: 478

Text #10

Max Range: 1.8392. Min Range: -1.8392

Max Act: 1.7359. Min Act: -0.1700

Data Index: 2615281 (Open Web Text)

Max Activating Token Index: 67

Text #11

Max Range: 1.8392. Min Range: -1.8392

Max Act: 1.7470. Min Act: -0.1700

Data Index: 2247790 (Open Web Text)

Max Activating Token Index: 31

Text #12

Max Range: 1.8392. Min Range: -1.8392

Max Act: 1.7426. Min Act: -0.1700

Data Index: 2298582 (Open Web Text)

Max Activating Token Index: 282

Text #13

Max Range: 1.8392. Min Range: -1.8392

Max Act: 1.7347. Min Act: -0.1700

Data Index: 7299981 (Open Web Text)

Max Activating Token Index: 545

Text #14

Max Range: 1.8392. Min Range: -1.8392

Max Act: 1.7409. Min Act: -0.1700

Data Index: 7674486 (Open Web Text)

Max Activating Token Index: 561

Text #15

Max Range: 1.8392. Min Range: -1.8392

Max Act: 1.7349. Min Act: -0.1700

Data Index: 1583128 (Open Web Text)

Max Activating Token Index: 254

Text #16

Max Range: 1.8392. Min Range: -1.8392

Max Act: 1.7331. Min Act: -0.1700

Data Index: 8772619 (Open Web Text)

Max Activating Token Index: 221

Text #17

Max Range: 1.8392. Min Range: -1.8392

Max Act: 1.7319. Min Act: -0.1700

Data Index: 7781303 (Open Web Text)

Max Activating Token Index: 324

Text #18

Max Range: 1.8392. Min Range: -1.8392

Max Act: 1.7187. Min Act: -0.1700

Data Index: 4658387 (Open Web Text)

Max Activating Token Index: 331

Text #19

Max Range: 1.8392. Min Range: -1.8392

Max Act: 1.7278. Min Act: -0.1700

Data Index: 6173771 (Open Web Text)

Max Activating Token Index: 502