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

Dataset: Open Web Text

Neuron 2259 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: 3.7936. Min Range: -3.7936

Max Act: 3.7936. Min Act: -0.1700

Data Index: 2781646 (Open Web Text)

Max Activating Token Index: 827

Text #1

Max Range: 3.7936. Min Range: -3.7936

Max Act: 3.7474. Min Act: -0.1700

Data Index: 144438 (Open Web Text)

Max Activating Token Index: 475

Text #2

Max Range: 3.7936. Min Range: -3.7936

Max Act: 3.7376. Min Act: -0.1700

Data Index: 6554055 (Open Web Text)

Max Activating Token Index: 864

Text #3

Max Range: 3.7936. Min Range: -3.7936

Max Act: 3.7705. Min Act: -0.1700

Data Index: 6668438 (Open Web Text)

Max Activating Token Index: 447

Text #4

Max Range: 3.7936. Min Range: -3.7936

Max Act: 3.7488. Min Act: -0.1700

Data Index: 6820611 (Open Web Text)

Max Activating Token Index: 291

Text #5

Max Range: 3.7936. Min Range: -3.7936

Max Act: 3.7398. Min Act: -0.1700

Data Index: 5577741 (Open Web Text)

Max Activating Token Index: 375

Text #6

Max Range: 3.7936. Min Range: -3.7936

Max Act: 3.6984. Min Act: -0.1700

Data Index: 450431 (Open Web Text)

Max Activating Token Index: 761

Text #7

Max Range: 3.7936. Min Range: -3.7936

Max Act: 3.7656. Min Act: -0.1700

Data Index: 2561266 (Open Web Text)

Max Activating Token Index: 951

Text #8

Max Range: 3.7936. Min Range: -3.7936

Max Act: 3.7179. Min Act: -0.1700

Data Index: 2426330 (Open Web Text)

Max Activating Token Index: 501

Text #9

Max Range: 3.7936. Min Range: -3.7936

Max Act: 3.7138. Min Act: -0.1700

Data Index: 56866 (Open Web Text)

Max Activating Token Index: 554

Text #10

Max Range: 3.7936. Min Range: -3.7936

Max Act: 3.7261. Min Act: -0.1700

Data Index: 2422595 (Open Web Text)

Max Activating Token Index: 602

Text #11

Max Range: 3.7936. Min Range: -3.7936

Max Act: 3.7196. Min Act: -0.1700

Data Index: 5855176 (Open Web Text)

Max Activating Token Index: 940

Text #12

Max Range: 3.7936. Min Range: -3.7936

Max Act: 3.6963. Min Act: -0.1700

Data Index: 2022764 (Open Web Text)

Max Activating Token Index: 751

Text #13

Max Range: 3.7936. Min Range: -3.7936

Max Act: 3.6981. Min Act: -0.1700

Data Index: 4998988 (Open Web Text)

Max Activating Token Index: 914

Text #14

Max Range: 3.7936. Min Range: -3.7936

Max Act: 3.7112. Min Act: -0.1700

Data Index: 7781728 (Open Web Text)

Max Activating Token Index: 469

Text #15

Max Range: 3.7936. Min Range: -3.7936

Max Act: 3.7316. Min Act: -0.1700

Data Index: 7063981 (Open Web Text)

Max Activating Token Index: 579

Text #16

Max Range: 3.7936. Min Range: -3.7936

Max Act: 3.7416. Min Act: -0.1700

Data Index: 1764033 (Open Web Text)

Max Activating Token Index: 445

Text #17

Max Range: 3.7936. Min Range: -3.7936

Max Act: 3.6911. Min Act: -0.1700

Data Index: 1594345 (Open Web Text)

Max Activating Token Index: 902

Text #18

Max Range: 3.7936. Min Range: -3.7936

Max Act: 3.6876. Min Act: -0.1700

Data Index: 5171574 (Open Web Text)

Max Activating Token Index: 729

Text #19

Max Range: 3.7936. Min Range: -3.7936

Max Act: 3.6835. Min Act: -0.1700

Data Index: 6192244 (Open Web Text)

Max Activating Token Index: 827