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

Dataset: Open Web Text

Neuron 2221 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: 3.4081. Min Range: -3.4081

Max Act: 3.4081. Min Act: -0.1700

Data Index: 5105192 (Open Web Text)

Max Activating Token Index: 878

Text #1

Max Range: 3.4081. Min Range: -3.4081

Max Act: 3.2682. Min Act: -0.1700

Data Index: 7039897 (Open Web Text)

Max Activating Token Index: 254

Text #2

Max Range: 3.4081. Min Range: -3.4081

Max Act: 3.2177. Min Act: -0.1700

Data Index: 3463063 (Open Web Text)

Max Activating Token Index: 195

Text #3

Max Range: 3.4081. Min Range: -3.4081

Max Act: 3.1602. Min Act: -0.1700

Data Index: 3437532 (Open Web Text)

Max Activating Token Index: 948

Text #4

Max Range: 3.4081. Min Range: -3.4081

Max Act: 3.1251. Min Act: -0.1700

Data Index: 3033793 (Open Web Text)

Max Activating Token Index: 434

Text #5

Max Range: 3.4081. Min Range: -3.4081

Max Act: 3.1146. Min Act: -0.1700

Data Index: 2530648 (Open Web Text)

Max Activating Token Index: 357

Text #6

Max Range: 3.4081. Min Range: -3.4081

Max Act: 3.1204. Min Act: -0.1700

Data Index: 3340495 (Open Web Text)

Max Activating Token Index: 398

Text #7

Max Range: 3.4081. Min Range: -3.4081

Max Act: 3.1146. Min Act: -0.1700

Data Index: 5189953 (Open Web Text)

Max Activating Token Index: 940

Text #8

Max Range: 3.4081. Min Range: -3.4081

Max Act: 3.0496. Min Act: -0.1700

Data Index: 4221261 (Open Web Text)

Max Activating Token Index: 843

Text #9

Max Range: 3.4081. Min Range: -3.4081

Max Act: 3.0910. Min Act: -0.1700

Data Index: 3580275 (Open Web Text)

Max Activating Token Index: 68

Text #10

Max Range: 3.4081. Min Range: -3.4081

Max Act: 3.0777. Min Act: -0.1700

Data Index: 1767316 (Open Web Text)

Max Activating Token Index: 450

Text #11

Max Range: 3.4081. Min Range: -3.4081

Max Act: 3.0831. Min Act: -0.1700

Data Index: 875426 (Open Web Text)

Max Activating Token Index: 737

Text #12

Max Range: 3.4081. Min Range: -3.4081

Max Act: 3.0555. Min Act: -0.1700

Data Index: 1252340 (Open Web Text)

Max Activating Token Index: 1006

Text #13

Max Range: 3.4081. Min Range: -3.4081

Max Act: 3.0658. Min Act: -0.1700

Data Index: 7276146 (Open Web Text)

Max Activating Token Index: 383

Text #14

Max Range: 3.4081. Min Range: -3.4081

Max Act: 3.0595. Min Act: -0.1700

Data Index: 7621186 (Open Web Text)

Max Activating Token Index: 352

Text #15

Max Range: 3.4081. Min Range: -3.4081

Max Act: 3.0778. Min Act: -0.1700

Data Index: 8555480 (Open Web Text)

Max Activating Token Index: 402

Text #16

Max Range: 3.4081. Min Range: -3.4081

Max Act: 3.0324. Min Act: -0.1700

Data Index: 7077095 (Open Web Text)

Max Activating Token Index: 478

Text #17

Max Range: 3.4081. Min Range: -3.4081

Max Act: 3.0345. Min Act: -0.1700

Data Index: 8410692 (Open Web Text)

Max Activating Token Index: 489

Text #18

Max Range: 3.4081. Min Range: -3.4081

Max Act: 3.0235. Min Act: -0.1700

Data Index: 4133198 (Open Web Text)

Max Activating Token Index: 905

Text #19

Max Range: 3.4081. Min Range: -3.4081

Max Act: 3.0485. Min Act: -0.1700

Data Index: 5499126 (Open Web Text)

Max Activating Token Index: 260