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

Dataset: Open Web Text

Neuron 2638 in Layer 3

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: 3.3767. Min Range: -3.3767

Max Act: 3.3767. Min Act: -0.1700

Data Index: 5250969 (Open Web Text)

Max Activating Token Index: 464

Text #1

Max Range: 3.3767. Min Range: -3.3767

Max Act: 3.3064. Min Act: -0.1700

Data Index: 7122191 (Open Web Text)

Max Activating Token Index: 923

Text #2

Max Range: 3.3767. Min Range: -3.3767

Max Act: 3.3039. Min Act: -0.1700

Data Index: 1918849 (Open Web Text)

Max Activating Token Index: 875

Text #3

Max Range: 3.3767. Min Range: -3.3767

Max Act: 3.2691. Min Act: -0.1700

Data Index: 4574720 (Open Web Text)

Max Activating Token Index: 21

Text #4

Max Range: 3.3767. Min Range: -3.3767

Max Act: 3.2726. Min Act: -0.1700

Data Index: 5381467 (Open Web Text)

Max Activating Token Index: 1001

Text #5

Max Range: 3.3767. Min Range: -3.3767

Max Act: 3.2755. Min Act: -0.1700

Data Index: 3451692 (Open Web Text)

Max Activating Token Index: 1019

Text #6

Max Range: 3.3767. Min Range: -3.3767

Max Act: 3.2617. Min Act: -0.1700

Data Index: 7718270 (Open Web Text)

Max Activating Token Index: 346

Text #7

Max Range: 3.3767. Min Range: -3.3767

Max Act: 3.2528. Min Act: -0.1700

Data Index: 8088834 (Open Web Text)

Max Activating Token Index: 106

Text #8

Max Range: 3.3767. Min Range: -3.3767

Max Act: 3.2690. Min Act: -0.1700

Data Index: 1713986 (Open Web Text)

Max Activating Token Index: 281

Text #9

Max Range: 3.3767. Min Range: -3.3767

Max Act: 3.2382. Min Act: -0.1700

Data Index: 3451693 (Open Web Text)

Max Activating Token Index: 13

Text #10

Max Range: 3.3767. Min Range: -3.3767

Max Act: 3.2320. Min Act: -0.1700

Data Index: 4760219 (Open Web Text)

Max Activating Token Index: 8

Text #11

Max Range: 3.3767. Min Range: -3.3767

Max Act: 3.2095. Min Act: -0.1700

Data Index: 5387181 (Open Web Text)

Max Activating Token Index: 496

Text #12

Max Range: 3.3767. Min Range: -3.3767

Max Act: 3.2287. Min Act: -0.1700

Data Index: 3177089 (Open Web Text)

Max Activating Token Index: 432

Text #13

Max Range: 3.3767. Min Range: -3.3767

Max Act: 3.2010. Min Act: -0.1700

Data Index: 8488016 (Open Web Text)

Max Activating Token Index: 526

Text #14

Max Range: 3.3767. Min Range: -3.3767

Max Act: 3.2218. Min Act: -0.1700

Data Index: 4704915 (Open Web Text)

Max Activating Token Index: 254

Text #15

Max Range: 3.3767. Min Range: -3.3767

Max Act: 3.2165. Min Act: -0.1700

Data Index: 521960 (Open Web Text)

Max Activating Token Index: 23

Text #16

Max Range: 3.3767. Min Range: -3.3767

Max Act: 3.2212. Min Act: -0.1700

Data Index: 8340765 (Open Web Text)

Max Activating Token Index: 769

Text #17

Max Range: 3.3767. Min Range: -3.3767

Max Act: 3.2116. Min Act: -0.1700

Data Index: 7253003 (Open Web Text)

Max Activating Token Index: 341

Text #18

Max Range: 3.3767. Min Range: -3.3767

Max Act: 3.1634. Min Act: -0.1700

Data Index: 632181 (Open Web Text)

Max Activating Token Index: 36

Text #19

Max Range: 3.3767. Min Range: -3.3767

Max Act: 3.1818. Min Act: -0.1700

Data Index: 7574044 (Open Web Text)

Max Activating Token Index: 528