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

Dataset: Open Web Text

Neuron 967 in Layer 3

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: 3.7634. Min Range: -3.7634

Max Act: 3.7634. Min Act: -0.1700

Data Index: 1309229 (Open Web Text)

Max Activating Token Index: 893

Text #1

Max Range: 3.7634. Min Range: -3.7634

Max Act: 3.6881. Min Act: -0.1700

Data Index: 4720625 (Open Web Text)

Max Activating Token Index: 876

Text #2

Max Range: 3.7634. Min Range: -3.7634

Max Act: 3.6706. Min Act: -0.1700

Data Index: 8553098 (Open Web Text)

Max Activating Token Index: 89

Text #3

Max Range: 3.7634. Min Range: -3.7634

Max Act: 3.6252. Min Act: -0.1700

Data Index: 5913467 (Open Web Text)

Max Activating Token Index: 418

Text #4

Max Range: 3.7634. Min Range: -3.7634

Max Act: 3.6309. Min Act: -0.1700

Data Index: 2310606 (Open Web Text)

Max Activating Token Index: 632

Text #5

Max Range: 3.7634. Min Range: -3.7634

Max Act: 3.5904. Min Act: -0.1700

Data Index: 1426912 (Open Web Text)

Max Activating Token Index: 300

Text #6

Max Range: 3.7634. Min Range: -3.7634

Max Act: 3.5935. Min Act: -0.1700

Data Index: 3863822 (Open Web Text)

Max Activating Token Index: 908

Text #7

Max Range: 3.7634. Min Range: -3.7634

Max Act: 3.5890. Min Act: -0.1698

Data Index: 8594614 (Open Web Text)

Max Activating Token Index: 292

Text #8

Max Range: 3.7634. Min Range: -3.7634

Max Act: 3.5801. Min Act: -0.1700

Data Index: 8019641 (Open Web Text)

Max Activating Token Index: 702

Text #9

Max Range: 3.7634. Min Range: -3.7634

Max Act: 3.5393. Min Act: -0.1699

Data Index: 1342412 (Open Web Text)

Max Activating Token Index: 103

Text #10

Max Range: 3.7634. Min Range: -3.7634

Max Act: 3.5751. Min Act: -0.1700

Data Index: 3887605 (Open Web Text)

Max Activating Token Index: 697

Text #11

Max Range: 3.7634. Min Range: -3.7634

Max Act: 3.5332. Min Act: -0.1700

Data Index: 335931 (Open Web Text)

Max Activating Token Index: 787

Text #12

Max Range: 3.7634. Min Range: -3.7634

Max Act: 3.5466. Min Act: -0.1700

Data Index: 3020086 (Open Web Text)

Max Activating Token Index: 531

Text #13

Max Range: 3.7634. Min Range: -3.7634

Max Act: 3.5483. Min Act: -0.1700

Data Index: 6689602 (Open Web Text)

Max Activating Token Index: 193

Text #14

Max Range: 3.7634. Min Range: -3.7634

Max Act: 3.5353. Min Act: -0.1700

Data Index: 7823654 (Open Web Text)

Max Activating Token Index: 564

Text #15

Max Range: 3.7634. Min Range: -3.7634

Max Act: 3.5333. Min Act: -0.1700

Data Index: 7720475 (Open Web Text)

Max Activating Token Index: 46

Text #16

Max Range: 3.7634. Min Range: -3.7634

Max Act: 3.5487. Min Act: -0.1700

Data Index: 1206213 (Open Web Text)

Max Activating Token Index: 494

Text #17

Max Range: 3.7634. Min Range: -3.7634

Max Act: 3.5338. Min Act: -0.1700

Data Index: 7240451 (Open Web Text)

Max Activating Token Index: 121

Text #18

Max Range: 3.7634. Min Range: -3.7634

Max Act: 3.4908. Min Act: -0.1699

Data Index: 1330283 (Open Web Text)

Max Activating Token Index: 401

Text #19

Max Range: 3.7634. Min Range: -3.7634

Max Act: 3.5162. Min Act: -0.1700

Data Index: 4267762 (Open Web Text)

Max Activating Token Index: 716