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

Dataset: Open Web Text

Neuron 2669 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: 3.7393. Min Range: -3.7393

Max Act: 3.7393. Min Act: -0.1700

Data Index: 4922031 (Open Web Text)

Max Activating Token Index: 145

Text #1

Max Range: 3.7393. Min Range: -3.7393

Max Act: 3.7130. Min Act: -0.1700

Data Index: 1644712 (Open Web Text)

Max Activating Token Index: 602

Text #2

Max Range: 3.7393. Min Range: -3.7393

Max Act: 3.6787. Min Act: -0.1700

Data Index: 7856029 (Open Web Text)

Max Activating Token Index: 311

Text #3

Max Range: 3.7393. Min Range: -3.7393

Max Act: 3.6843. Min Act: -0.1700

Data Index: 3160698 (Open Web Text)

Max Activating Token Index: 945

Text #4

Max Range: 3.7393. Min Range: -3.7393

Max Act: 3.6605. Min Act: -0.1700

Data Index: 3692647 (Open Web Text)

Max Activating Token Index: 709

Text #5

Max Range: 3.7393. Min Range: -3.7393

Max Act: 3.6553. Min Act: -0.1700

Data Index: 3905246 (Open Web Text)

Max Activating Token Index: 703

Text #6

Max Range: 3.7393. Min Range: -3.7393

Max Act: 3.6445. Min Act: -0.1700

Data Index: 3406048 (Open Web Text)

Max Activating Token Index: 765

Text #7

Max Range: 3.7393. Min Range: -3.7393

Max Act: 3.6407. Min Act: -0.1700

Data Index: 343089 (Open Web Text)

Max Activating Token Index: 146

Text #8

Max Range: 3.7393. Min Range: -3.7393

Max Act: 3.6315. Min Act: -0.1700

Data Index: 2426863 (Open Web Text)

Max Activating Token Index: 414

Text #9

Max Range: 3.7393. Min Range: -3.7393

Max Act: 3.6005. Min Act: -0.1700

Data Index: 514448 (Open Web Text)

Max Activating Token Index: 899

Text #10

Max Range: 3.7393. Min Range: -3.7393

Max Act: 3.6038. Min Act: -0.1700

Data Index: 1489338 (Open Web Text)

Max Activating Token Index: 941

Text #11

Max Range: 3.7393. Min Range: -3.7393

Max Act: 3.6180. Min Act: -0.1700

Data Index: 1468436 (Open Web Text)

Max Activating Token Index: 175

Text #12

Max Range: 3.7393. Min Range: -3.7393

Max Act: 3.6016. Min Act: -0.1700

Data Index: 3539319 (Open Web Text)

Max Activating Token Index: 271

Text #13

Max Range: 3.7393. Min Range: -3.7393

Max Act: 3.6062. Min Act: -0.1700

Data Index: 7274679 (Open Web Text)

Max Activating Token Index: 360

Text #14

Max Range: 3.7393. Min Range: -3.7393

Max Act: 3.5886. Min Act: -0.1700

Data Index: 8017029 (Open Web Text)

Max Activating Token Index: 140

Text #15

Max Range: 3.7393. Min Range: -3.7393

Max Act: 3.5752. Min Act: -0.1700

Data Index: 7689100 (Open Web Text)

Max Activating Token Index: 773

Text #16

Max Range: 3.7393. Min Range: -3.7393

Max Act: 3.5783. Min Act: -0.1700

Data Index: 6343526 (Open Web Text)

Max Activating Token Index: 103

Text #17

Max Range: 3.7393. Min Range: -3.7393

Max Act: 3.5939. Min Act: -0.1700

Data Index: 2234592 (Open Web Text)

Max Activating Token Index: 751

Text #18

Max Range: 3.7393. Min Range: -3.7393

Max Act: 3.5832. Min Act: -0.1700

Data Index: 5521438 (Open Web Text)

Max Activating Token Index: 765

Text #19

Max Range: 3.7393. Min Range: -3.7393

Max Act: 3.5659. Min Act: -0.1700

Data Index: 8164096 (Open Web Text)

Max Activating Token Index: 772