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

Dataset: Open Web Text

Neuron 1722 in Layer 2

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: 3.4326. Min Range: -3.4326

Max Act: 3.4326. Min Act: -0.1700

Data Index: 2511941 (Open Web Text)

Max Activating Token Index: 40

Text #1

Max Range: 3.4326. Min Range: -3.4326

Max Act: 3.4073. Min Act: -0.1700

Data Index: 1016941 (Open Web Text)

Max Activating Token Index: 859

Text #2

Max Range: 3.4326. Min Range: -3.4326

Max Act: 3.3559. Min Act: -0.1700

Data Index: 7017221 (Open Web Text)

Max Activating Token Index: 812

Text #3

Max Range: 3.4326. Min Range: -3.4326

Max Act: 3.3172. Min Act: -0.1700

Data Index: 2399938 (Open Web Text)

Max Activating Token Index: 741

Text #4

Max Range: 3.4326. Min Range: -3.4326

Max Act: 3.3146. Min Act: -0.1700

Data Index: 1536069 (Open Web Text)

Max Activating Token Index: 458

Text #5

Max Range: 3.4326. Min Range: -3.4326

Max Act: 3.3091. Min Act: -0.1700

Data Index: 6701931 (Open Web Text)

Max Activating Token Index: 177

Text #6

Max Range: 3.4326. Min Range: -3.4326

Max Act: 3.2910. Min Act: -0.1700

Data Index: 7221745 (Open Web Text)

Max Activating Token Index: 252

Text #7

Max Range: 3.4326. Min Range: -3.4326

Max Act: 3.2879. Min Act: -0.1700

Data Index: 6433565 (Open Web Text)

Max Activating Token Index: 67

Text #8

Max Range: 3.4326. Min Range: -3.4326

Max Act: 3.2803. Min Act: -0.1700

Data Index: 7565688 (Open Web Text)

Max Activating Token Index: 345

Text #9

Max Range: 3.4326. Min Range: -3.4326

Max Act: 3.2640. Min Act: -0.1700

Data Index: 175942 (Open Web Text)

Max Activating Token Index: 646

Text #10

Max Range: 3.4326. Min Range: -3.4326

Max Act: 3.2708. Min Act: -0.1700

Data Index: 6697709 (Open Web Text)

Max Activating Token Index: 937

Text #11

Max Range: 3.4326. Min Range: -3.4326

Max Act: 3.2642. Min Act: -0.1700

Data Index: 3829148 (Open Web Text)

Max Activating Token Index: 882

Text #12

Max Range: 3.4326. Min Range: -3.4326

Max Act: 3.2725. Min Act: -0.1700

Data Index: 2694705 (Open Web Text)

Max Activating Token Index: 126

Text #13

Max Range: 3.4326. Min Range: -3.4326

Max Act: 3.2622. Min Act: -0.1700

Data Index: 7138777 (Open Web Text)

Max Activating Token Index: 25

Text #14

Max Range: 3.4326. Min Range: -3.4326

Max Act: 3.2670. Min Act: -0.1700

Data Index: 7820818 (Open Web Text)

Max Activating Token Index: 274

Text #15

Max Range: 3.4326. Min Range: -3.4326

Max Act: 3.2492. Min Act: -0.1700

Data Index: 5319312 (Open Web Text)

Max Activating Token Index: 70

Text #16

Max Range: 3.4326. Min Range: -3.4326

Max Act: 3.2509. Min Act: -0.1700

Data Index: 4416355 (Open Web Text)

Max Activating Token Index: 969

Text #17

Max Range: 3.4326. Min Range: -3.4326

Max Act: 3.2267. Min Act: -0.1700

Data Index: 6368983 (Open Web Text)

Max Activating Token Index: 957

Text #18

Max Range: 3.4326. Min Range: -3.4326

Max Act: 3.2268. Min Act: -0.1700

Data Index: 7156947 (Open Web Text)

Max Activating Token Index: 67

Text #19

Max Range: 3.4326. Min Range: -3.4326

Max Act: 3.2282. Min Act: -0.1700

Data Index: 2244809 (Open Web Text)

Max Activating Token Index: 64