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

Dataset: Open Web Text

Neuron 764 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: 3.5352. Min Range: -3.5352

Max Act: 3.5352. Min Act: -0.1700

Data Index: 7024961 (Open Web Text)

Max Activating Token Index: 1023

Text #1

Max Range: 3.5352. Min Range: -3.5352

Max Act: 3.5005. Min Act: -0.1700

Data Index: 6893544 (Open Web Text)

Max Activating Token Index: 449

Text #2

Max Range: 3.5352. Min Range: -3.5352

Max Act: 3.4920. Min Act: -0.1700

Data Index: 7849421 (Open Web Text)

Max Activating Token Index: 32

Text #3

Max Range: 3.5352. Min Range: -3.5352

Max Act: 3.4433. Min Act: -0.1700

Data Index: 5813541 (Open Web Text)

Max Activating Token Index: 525

Text #4

Max Range: 3.5352. Min Range: -3.5352

Max Act: 3.4285. Min Act: -0.1700

Data Index: 1468338 (Open Web Text)

Max Activating Token Index: 534

Text #5

Max Range: 3.5352. Min Range: -3.5352

Max Act: 3.4240. Min Act: -0.1700

Data Index: 5876924 (Open Web Text)

Max Activating Token Index: 946

Text #6

Max Range: 3.5352. Min Range: -3.5352

Max Act: 3.4073. Min Act: -0.1700

Data Index: 19167 (Open Web Text)

Max Activating Token Index: 362

Text #7

Max Range: 3.5352. Min Range: -3.5352

Max Act: 3.4305. Min Act: -0.1700

Data Index: 7024962 (Open Web Text)

Max Activating Token Index: 98

Text #8

Max Range: 3.5352. Min Range: -3.5352

Max Act: 3.3969. Min Act: -0.1700

Data Index: 8200173 (Open Web Text)

Max Activating Token Index: 492

Text #9

Max Range: 3.5352. Min Range: -3.5352

Max Act: 3.3995. Min Act: -0.1700

Data Index: 7807318 (Open Web Text)

Max Activating Token Index: 874

Text #10

Max Range: 3.5352. Min Range: -3.5352

Max Act: 3.3678. Min Act: -0.1700

Data Index: 8111312 (Open Web Text)

Max Activating Token Index: 306

Text #11

Max Range: 3.5352. Min Range: -3.5352

Max Act: 3.3627. Min Act: -0.1700

Data Index: 6075350 (Open Web Text)

Max Activating Token Index: 417

Text #12

Max Range: 3.5352. Min Range: -3.5352

Max Act: 3.3140. Min Act: -0.1700

Data Index: 1714407 (Open Web Text)

Max Activating Token Index: 577

Text #13

Max Range: 3.5352. Min Range: -3.5352

Max Act: 3.3040. Min Act: -0.1700

Data Index: 3952418 (Open Web Text)

Max Activating Token Index: 487

Text #14

Max Range: 3.5352. Min Range: -3.5352

Max Act: 3.2922. Min Act: -0.1700

Data Index: 8124814 (Open Web Text)

Max Activating Token Index: 448

Text #15

Max Range: 3.5352. Min Range: -3.5352

Max Act: 3.2795. Min Act: -0.1700

Data Index: 1036063 (Open Web Text)

Max Activating Token Index: 54

Text #16

Max Range: 3.5352. Min Range: -3.5352

Max Act: 3.2412. Min Act: -0.1700

Data Index: 5474115 (Open Web Text)

Max Activating Token Index: 455

Text #17

Max Range: 3.5352. Min Range: -3.5352

Max Act: 3.2732. Min Act: -0.1700

Data Index: 3234890 (Open Web Text)

Max Activating Token Index: 105

Text #18

Max Range: 3.5352. Min Range: -3.5352

Max Act: 3.2762. Min Act: -0.1700

Data Index: 1193191 (Open Web Text)

Max Activating Token Index: 925

Text #19

Max Range: 3.5352. Min Range: -3.5352

Max Act: 3.2662. Min Act: -0.1700

Data Index: 3013815 (Open Web Text)

Max Activating Token Index: 21