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

Dataset: Open Web Text

Neuron 1739 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: 4.6339. Min Range: -4.6339

Max Act: 4.6339. Min Act: -0.1700

Data Index: 2510805 (Open Web Text)

Max Activating Token Index: 430

Text #1

Max Range: 4.6339. Min Range: -4.6339

Max Act: 4.2744. Min Act: -0.1700

Data Index: 7886919 (Open Web Text)

Max Activating Token Index: 340

Text #2

Max Range: 4.6339. Min Range: -4.6339

Max Act: 4.2843. Min Act: -0.1700

Data Index: 609021 (Open Web Text)

Max Activating Token Index: 986

Text #3

Max Range: 4.6339. Min Range: -4.6339

Max Act: 4.2272. Min Act: -0.1700

Data Index: 7209810 (Open Web Text)

Max Activating Token Index: 899

Text #4

Max Range: 4.6339. Min Range: -4.6339

Max Act: 4.0809. Min Act: -0.1700

Data Index: 8183455 (Open Web Text)

Max Activating Token Index: 482

Text #5

Max Range: 4.6339. Min Range: -4.6339

Max Act: 4.0172. Min Act: -0.1700

Data Index: 5564234 (Open Web Text)

Max Activating Token Index: 128

Text #6

Max Range: 4.6339. Min Range: -4.6339

Max Act: 3.9916. Min Act: -0.1700

Data Index: 5600818 (Open Web Text)

Max Activating Token Index: 1008

Text #7

Max Range: 4.6339. Min Range: -4.6339

Max Act: 3.9641. Min Act: -0.1700

Data Index: 7115971 (Open Web Text)

Max Activating Token Index: 343

Text #8

Max Range: 4.6339. Min Range: -4.6339

Max Act: 3.9608. Min Act: -0.1700

Data Index: 2479959 (Open Web Text)

Max Activating Token Index: 170

Text #9

Max Range: 4.6339. Min Range: -4.6339

Max Act: 3.9483. Min Act: -0.1700

Data Index: 4472614 (Open Web Text)

Max Activating Token Index: 1023

Text #10

Max Range: 4.6339. Min Range: -4.6339

Max Act: 3.9672. Min Act: -0.1700

Data Index: 7865171 (Open Web Text)

Max Activating Token Index: 443

Text #11

Max Range: 4.6339. Min Range: -4.6339

Max Act: 3.9483. Min Act: -0.1700

Data Index: 1187845 (Open Web Text)

Max Activating Token Index: 223

Text #12

Max Range: 4.6339. Min Range: -4.6339

Max Act: 3.9488. Min Act: -0.1700

Data Index: 7755325 (Open Web Text)

Max Activating Token Index: 823

Text #13

Max Range: 4.6339. Min Range: -4.6339

Max Act: 3.9507. Min Act: -0.1700

Data Index: 5230228 (Open Web Text)

Max Activating Token Index: 794

Text #14

Max Range: 4.6339. Min Range: -4.6339

Max Act: 3.9694. Min Act: -0.1700

Data Index: 1843939 (Open Web Text)

Max Activating Token Index: 863

Text #15

Max Range: 4.6339. Min Range: -4.6339

Max Act: 3.9640. Min Act: -0.1700

Data Index: 6426492 (Open Web Text)

Max Activating Token Index: 567

Text #16

Max Range: 4.6339. Min Range: -4.6339

Max Act: 3.9385. Min Act: -0.1700

Data Index: 4092202 (Open Web Text)

Max Activating Token Index: 525

Text #17

Max Range: 4.6339. Min Range: -4.6339

Max Act: 3.9276. Min Act: -0.1700

Data Index: 98568 (Open Web Text)

Max Activating Token Index: 753

Text #18

Max Range: 4.6339. Min Range: -4.6339

Max Act: 3.9595. Min Act: -0.1700

Data Index: 2161524 (Open Web Text)

Max Activating Token Index: 963

Text #19

Max Range: 4.6339. Min Range: -4.6339

Max Act: 3.9589. Min Act: -0.1700

Data Index: 724729 (Open Web Text)

Max Activating Token Index: 681