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

Dataset: Open Web Text

Neuron 2541 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: 3.1802. Min Range: -3.1802

Max Act: 3.1802. Min Act: -0.1700

Data Index: 5442211 (Open Web Text)

Max Activating Token Index: 850

Text #1

Max Range: 3.1802. Min Range: -3.1802

Max Act: 3.1527. Min Act: -0.1700

Data Index: 1456137 (Open Web Text)

Max Activating Token Index: 216

Text #2

Max Range: 3.1802. Min Range: -3.1802

Max Act: 3.1337. Min Act: -0.1700

Data Index: 1593764 (Open Web Text)

Max Activating Token Index: 186

Text #3

Max Range: 3.1802. Min Range: -3.1802

Max Act: 3.1161. Min Act: -0.1700

Data Index: 7078910 (Open Web Text)

Max Activating Token Index: 365

Text #4

Max Range: 3.1802. Min Range: -3.1802

Max Act: 3.1066. Min Act: -0.1700

Data Index: 3968252 (Open Web Text)

Max Activating Token Index: 926

Text #5

Max Range: 3.1802. Min Range: -3.1802

Max Act: 3.0845. Min Act: -0.1700

Data Index: 1951403 (Open Web Text)

Max Activating Token Index: 386

Text #6

Max Range: 3.1802. Min Range: -3.1802

Max Act: 3.0871. Min Act: -0.1700

Data Index: 8567441 (Open Web Text)

Max Activating Token Index: 930

Text #7

Max Range: 3.1802. Min Range: -3.1802

Max Act: 3.0878. Min Act: -0.1700

Data Index: 5166440 (Open Web Text)

Max Activating Token Index: 456

Text #8

Max Range: 3.1802. Min Range: -3.1802

Max Act: 3.0637. Min Act: -0.1700

Data Index: 2398762 (Open Web Text)

Max Activating Token Index: 887

Text #9

Max Range: 3.1802. Min Range: -3.1802

Max Act: 3.0553. Min Act: -0.1700

Data Index: 964803 (Open Web Text)

Max Activating Token Index: 657

Text #10

Max Range: 3.1802. Min Range: -3.1802

Max Act: 3.0639. Min Act: -0.1700

Data Index: 5221472 (Open Web Text)

Max Activating Token Index: 734

Text #11

Max Range: 3.1802. Min Range: -3.1802

Max Act: 3.0746. Min Act: -0.1700

Data Index: 883759 (Open Web Text)

Max Activating Token Index: 354

Text #12

Max Range: 3.1802. Min Range: -3.1802

Max Act: 3.0332. Min Act: -0.1700

Data Index: 824040 (Open Web Text)

Max Activating Token Index: 334

Text #13

Max Range: 3.1802. Min Range: -3.1802

Max Act: 3.0467. Min Act: -0.1700

Data Index: 3591219 (Open Web Text)

Max Activating Token Index: 756

Text #14

Max Range: 3.1802. Min Range: -3.1802

Max Act: 3.0135. Min Act: -0.1700

Data Index: 369346 (Open Web Text)

Max Activating Token Index: 511

Text #15

Max Range: 3.1802. Min Range: -3.1802

Max Act: 3.0188. Min Act: -0.1700

Data Index: 2870307 (Open Web Text)

Max Activating Token Index: 213

Text #16

Max Range: 3.1802. Min Range: -3.1802

Max Act: 3.0204. Min Act: -0.1700

Data Index: 5844165 (Open Web Text)

Max Activating Token Index: 617

Text #17

Max Range: 3.1802. Min Range: -3.1802

Max Act: 3.0144. Min Act: -0.1700

Data Index: 2687545 (Open Web Text)

Max Activating Token Index: 713

Text #18

Max Range: 3.1802. Min Range: -3.1802

Max Act: 2.9983. Min Act: -0.1700

Data Index: 4574498 (Open Web Text)

Max Activating Token Index: 183

Text #19

Max Range: 3.1802. Min Range: -3.1802

Max Act: 3.0167. Min Act: -0.1700

Data Index: 214464 (Open Web Text)

Max Activating Token Index: 394