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

Dataset: Open Web Text

Neuron 2909 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: 4.2248. Min Range: -4.2248

Max Act: 4.2109. Min Act: -0.1700

Data Index: 7438580 (Open Web Text)

Max Activating Token Index: 688

Text #1

Max Range: 4.2248. Min Range: -4.2248

Max Act: 4.2248. Min Act: -0.1700

Data Index: 8498850 (Open Web Text)

Max Activating Token Index: 671

Text #2

Max Range: 4.2248. Min Range: -4.2248

Max Act: 4.2109. Min Act: -0.1700

Data Index: 270281 (Open Web Text)

Max Activating Token Index: 945

Text #3

Max Range: 4.2248. Min Range: -4.2248

Max Act: 4.1835. Min Act: -0.1700

Data Index: 8451073 (Open Web Text)

Max Activating Token Index: 601

Text #4

Max Range: 4.2248. Min Range: -4.2248

Max Act: 4.1298. Min Act: -0.1700

Data Index: 516438 (Open Web Text)

Max Activating Token Index: 280

Text #5

Max Range: 4.2248. Min Range: -4.2248

Max Act: 4.1384. Min Act: -0.1700

Data Index: 4809972 (Open Web Text)

Max Activating Token Index: 905

Text #6

Max Range: 4.2248. Min Range: -4.2248

Max Act: 4.1213. Min Act: -0.1700

Data Index: 3884621 (Open Web Text)

Max Activating Token Index: 295

Text #7

Max Range: 4.2248. Min Range: -4.2248

Max Act: 4.1154. Min Act: -0.1700

Data Index: 7326774 (Open Web Text)

Max Activating Token Index: 854

Text #8

Max Range: 4.2248. Min Range: -4.2248

Max Act: 4.1078. Min Act: -0.1700

Data Index: 5277350 (Open Web Text)

Max Activating Token Index: 429

Text #9

Max Range: 4.2248. Min Range: -4.2248

Max Act: 4.1180. Min Act: -0.1700

Data Index: 5239702 (Open Web Text)

Max Activating Token Index: 804

Text #10

Max Range: 4.2248. Min Range: -4.2248

Max Act: 4.0976. Min Act: -0.1700

Data Index: 1884492 (Open Web Text)

Max Activating Token Index: 941

Text #11

Max Range: 4.2248. Min Range: -4.2248

Max Act: 4.1423. Min Act: -0.1700

Data Index: 4385648 (Open Web Text)

Max Activating Token Index: 868

Text #12

Max Range: 4.2248. Min Range: -4.2248

Max Act: 4.1106. Min Act: -0.1700

Data Index: 1565941 (Open Web Text)

Max Activating Token Index: 846

Text #13

Max Range: 4.2248. Min Range: -4.2248

Max Act: 4.1341. Min Act: -0.1700

Data Index: 1330065 (Open Web Text)

Max Activating Token Index: 294

Text #14

Max Range: 4.2248. Min Range: -4.2248

Max Act: 4.0930. Min Act: -0.1700

Data Index: 382673 (Open Web Text)

Max Activating Token Index: 840

Text #15

Max Range: 4.2248. Min Range: -4.2248

Max Act: 4.0776. Min Act: -0.1700

Data Index: 4617068 (Open Web Text)

Max Activating Token Index: 698

Text #16

Max Range: 4.2248. Min Range: -4.2248

Max Act: 4.0701. Min Act: -0.1700

Data Index: 1686682 (Open Web Text)

Max Activating Token Index: 629

Text #17

Max Range: 4.2248. Min Range: -4.2248

Max Act: 4.0605. Min Act: -0.1700

Data Index: 318798 (Open Web Text)

Max Activating Token Index: 698

Text #18

Max Range: 4.2248. Min Range: -4.2248

Max Act: 4.0873. Min Act: -0.1700

Data Index: 306089 (Open Web Text)

Max Activating Token Index: 593

Text #19

Max Range: 4.2248. Min Range: -4.2248

Max Act: 4.0752. Min Act: -0.1700

Data Index: 3569345 (Open Web Text)

Max Activating Token Index: 625