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

Dataset: Open Web Text

Neuron 525 in Layer 5

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: 4.1326. Min Range: -4.1326

Max Act: 4.1326. Min Act: -0.1700

Data Index: 114870 (Open Web Text)

Max Activating Token Index: 65

Text #1

Max Range: 4.1326. Min Range: -4.1326

Max Act: 3.9824. Min Act: -0.1700

Data Index: 3620010 (Open Web Text)

Max Activating Token Index: 658

Text #2

Max Range: 4.1326. Min Range: -4.1326

Max Act: 3.9800. Min Act: -0.1700

Data Index: 7901954 (Open Web Text)

Max Activating Token Index: 324

Text #3

Max Range: 4.1326. Min Range: -4.1326

Max Act: 4.0061. Min Act: -0.1700

Data Index: 5090340 (Open Web Text)

Max Activating Token Index: 1008

Text #4

Max Range: 4.1326. Min Range: -4.1326

Max Act: 3.9450. Min Act: -0.1700

Data Index: 7901952 (Open Web Text)

Max Activating Token Index: 282

Text #5

Max Range: 4.1326. Min Range: -4.1326

Max Act: 3.9400. Min Act: -0.1700

Data Index: 3125531 (Open Web Text)

Max Activating Token Index: 718

Text #6

Max Range: 4.1326. Min Range: -4.1326

Max Act: 3.8901. Min Act: -0.1700

Data Index: 5083229 (Open Web Text)

Max Activating Token Index: 465

Text #7

Max Range: 4.1326. Min Range: -4.1326

Max Act: 3.9126. Min Act: -0.1700

Data Index: 278307 (Open Web Text)

Max Activating Token Index: 1023

Text #8

Max Range: 4.1326. Min Range: -4.1326

Max Act: 3.8814. Min Act: -0.1700

Data Index: 3286675 (Open Web Text)

Max Activating Token Index: 730

Text #9

Max Range: 4.1326. Min Range: -4.1326

Max Act: 3.8768. Min Act: -0.1700

Data Index: 1810141 (Open Web Text)

Max Activating Token Index: 435

Text #10

Max Range: 4.1326. Min Range: -4.1326

Max Act: 3.9081. Min Act: -0.1700

Data Index: 3248950 (Open Web Text)

Max Activating Token Index: 931

Text #11

Max Range: 4.1326. Min Range: -4.1326

Max Act: 3.8944. Min Act: -0.1700

Data Index: 7901951 (Open Web Text)

Max Activating Token Index: 798

Text #12

Max Range: 4.1326. Min Range: -4.1326

Max Act: 3.8656. Min Act: -0.1700

Data Index: 1889894 (Open Web Text)

Max Activating Token Index: 491

Text #13

Max Range: 4.1326. Min Range: -4.1326

Max Act: 3.8677. Min Act: -0.1700

Data Index: 8089729 (Open Web Text)

Max Activating Token Index: 703

Text #14

Max Range: 4.1326. Min Range: -4.1326

Max Act: 3.8498. Min Act: -0.1700

Data Index: 114871 (Open Web Text)

Max Activating Token Index: 153

Text #15

Max Range: 4.1326. Min Range: -4.1326

Max Act: 3.8943. Min Act: -0.1700

Data Index: 4671239 (Open Web Text)

Max Activating Token Index: 830

Text #16

Max Range: 4.1326. Min Range: -4.1326

Max Act: 3.8790. Min Act: -0.1700

Data Index: 1505506 (Open Web Text)

Max Activating Token Index: 70

Text #17

Max Range: 4.1326. Min Range: -4.1326

Max Act: 3.8334. Min Act: -0.1700

Data Index: 7901949 (Open Web Text)

Max Activating Token Index: 181

Text #18

Max Range: 4.1326. Min Range: -4.1326

Max Act: 3.8354. Min Act: -0.1700

Data Index: 4708592 (Open Web Text)

Max Activating Token Index: 781

Text #19

Max Range: 4.1326. Min Range: -4.1326

Max Act: 3.8125. Min Act: -0.1700

Data Index: 7217288 (Open Web Text)

Max Activating Token Index: 480