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

Dataset: Open Web Text

Neuron 1879 in Layer 0

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: 4.7162. Min Range: -4.7162

Max Act: 4.7162. Min Act: -0.1700

Data Index: 5165122 (Open Web Text)

Max Activating Token Index: 16

Text #1

Max Range: 4.7162. Min Range: -4.7162

Max Act: 4.6071. Min Act: -0.1700

Data Index: 2771385 (Open Web Text)

Max Activating Token Index: 362

Text #2

Max Range: 4.7162. Min Range: -4.7162

Max Act: 4.6030. Min Act: -0.1700

Data Index: 6989477 (Open Web Text)

Max Activating Token Index: 702

Text #3

Max Range: 4.7162. Min Range: -4.7162

Max Act: 4.5716. Min Act: -0.1700

Data Index: 6174160 (Open Web Text)

Max Activating Token Index: 845

Text #4

Max Range: 4.7162. Min Range: -4.7162

Max Act: 4.5599. Min Act: -0.1700

Data Index: 2879022 (Open Web Text)

Max Activating Token Index: 959

Text #5

Max Range: 4.7162. Min Range: -4.7162

Max Act: 4.5398. Min Act: -0.1700

Data Index: 4175566 (Open Web Text)

Max Activating Token Index: 1019

Text #6

Max Range: 4.7162. Min Range: -4.7162

Max Act: 4.5635. Min Act: -0.1700

Data Index: 5991541 (Open Web Text)

Max Activating Token Index: 1014

Text #7

Max Range: 4.7162. Min Range: -4.7162

Max Act: 4.5382. Min Act: -0.1700

Data Index: 6058943 (Open Web Text)

Max Activating Token Index: 915

Text #8

Max Range: 4.7162. Min Range: -4.7162

Max Act: 4.5257. Min Act: -0.1700

Data Index: 6935006 (Open Web Text)

Max Activating Token Index: 590

Text #9

Max Range: 4.7162. Min Range: -4.7162

Max Act: 4.5647. Min Act: -0.1700

Data Index: 3199910 (Open Web Text)

Max Activating Token Index: 722

Text #10

Max Range: 4.7162. Min Range: -4.7162

Max Act: 4.5091. Min Act: -0.1700

Data Index: 7434211 (Open Web Text)

Max Activating Token Index: 643

Text #11

Max Range: 4.7162. Min Range: -4.7162

Max Act: 4.5088. Min Act: -0.1700

Data Index: 4320501 (Open Web Text)

Max Activating Token Index: 761

Text #12

Max Range: 4.7162. Min Range: -4.7162

Max Act: 4.4977. Min Act: -0.1700

Data Index: 7198069 (Open Web Text)

Max Activating Token Index: 838

Text #13

Max Range: 4.7162. Min Range: -4.7162

Max Act: 4.5124. Min Act: -0.1700

Data Index: 3318151 (Open Web Text)

Max Activating Token Index: 6

Text #14

Max Range: 4.7162. Min Range: -4.7162

Max Act: 4.5066. Min Act: -0.1700

Data Index: 7122110 (Open Web Text)

Max Activating Token Index: 834

Text #15

Max Range: 4.7162. Min Range: -4.7162

Max Act: 4.5195. Min Act: -0.1700

Data Index: 439389 (Open Web Text)

Max Activating Token Index: 12

Text #16

Max Range: 4.7162. Min Range: -4.7162

Max Act: 4.5007. Min Act: -0.1700

Data Index: 4951093 (Open Web Text)

Max Activating Token Index: 916

Text #17

Max Range: 4.7162. Min Range: -4.7162

Max Act: 4.5154. Min Act: -0.1700

Data Index: 4894685 (Open Web Text)

Max Activating Token Index: 7

Text #18

Max Range: 4.7162. Min Range: -4.7162

Max Act: 4.5130. Min Act: -0.1700

Data Index: 4402152 (Open Web Text)

Max Activating Token Index: 22

Text #19

Max Range: 4.7162. Min Range: -4.7162

Max Act: 4.5023. Min Act: -0.1700

Data Index: 852460 (Open Web Text)

Max Activating Token Index: 1004