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

Dataset: Open Web Text

Neuron 1296 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: 3.8126. Min Range: -3.8126

Max Act: 3.8126. Min Act: -0.1700

Data Index: 4252533 (Open Web Text)

Max Activating Token Index: 368

Text #1

Max Range: 3.8126. Min Range: -3.8126

Max Act: 3.7147. Min Act: -0.1700

Data Index: 6992903 (Open Web Text)

Max Activating Token Index: 103

Text #2

Max Range: 3.8126. Min Range: -3.8126

Max Act: 3.7388. Min Act: -0.1700

Data Index: 8571069 (Open Web Text)

Max Activating Token Index: 568

Text #3

Max Range: 3.8126. Min Range: -3.8126

Max Act: 3.6856. Min Act: -0.1700

Data Index: 1140119 (Open Web Text)

Max Activating Token Index: 13

Text #4

Max Range: 3.8126. Min Range: -3.8126

Max Act: 3.6787. Min Act: -0.1700

Data Index: 8543654 (Open Web Text)

Max Activating Token Index: 521

Text #5

Max Range: 3.8126. Min Range: -3.8126

Max Act: 3.6591. Min Act: -0.1700

Data Index: 5094337 (Open Web Text)

Max Activating Token Index: 74

Text #6

Max Range: 3.8126. Min Range: -3.8126

Max Act: 3.6397. Min Act: -0.1700

Data Index: 4975014 (Open Web Text)

Max Activating Token Index: 926

Text #7

Max Range: 3.8126. Min Range: -3.8126

Max Act: 3.6641. Min Act: -0.1700

Data Index: 7005428 (Open Web Text)

Max Activating Token Index: 497

Text #8

Max Range: 3.8126. Min Range: -3.8126

Max Act: 3.6452. Min Act: -0.1700

Data Index: 3048975 (Open Web Text)

Max Activating Token Index: 51

Text #9

Max Range: 3.8126. Min Range: -3.8126

Max Act: 3.6586. Min Act: -0.1700

Data Index: 3990006 (Open Web Text)

Max Activating Token Index: 560

Text #10

Max Range: 3.8126. Min Range: -3.8126

Max Act: 3.6523. Min Act: -0.1700

Data Index: 6310244 (Open Web Text)

Max Activating Token Index: 13

Text #11

Max Range: 3.8126. Min Range: -3.8126

Max Act: 3.6464. Min Act: -0.1700

Data Index: 3122865 (Open Web Text)

Max Activating Token Index: 996

Text #12

Max Range: 3.8126. Min Range: -3.8126

Max Act: 3.5982. Min Act: -0.1700

Data Index: 6212198 (Open Web Text)

Max Activating Token Index: 479

Text #13

Max Range: 3.8126. Min Range: -3.8126

Max Act: 3.6133. Min Act: -0.1700

Data Index: 6012446 (Open Web Text)

Max Activating Token Index: 648

Text #14

Max Range: 3.8126. Min Range: -3.8126

Max Act: 3.6304. Min Act: -0.1700

Data Index: 3167199 (Open Web Text)

Max Activating Token Index: 550

Text #15

Max Range: 3.8126. Min Range: -3.8126

Max Act: 3.6390. Min Act: -0.1700

Data Index: 3392321 (Open Web Text)

Max Activating Token Index: 884

Text #16

Max Range: 3.8126. Min Range: -3.8126

Max Act: 3.5948. Min Act: -0.1700

Data Index: 436997 (Open Web Text)

Max Activating Token Index: 142

Text #17

Max Range: 3.8126. Min Range: -3.8126

Max Act: 3.6104. Min Act: -0.1700

Data Index: 8027665 (Open Web Text)

Max Activating Token Index: 671

Text #18

Max Range: 3.8126. Min Range: -3.8126

Max Act: 3.5717. Min Act: -0.1700

Data Index: 7777189 (Open Web Text)

Max Activating Token Index: 270

Text #19

Max Range: 3.8126. Min Range: -3.8126

Max Act: 3.5885. Min Act: -0.1700

Data Index: 481041 (Open Web Text)

Max Activating Token Index: 907