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

Dataset: Open Web Text

Neuron 1989 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: 4.7925. Min Range: -4.7925

Max Act: 4.7925. Min Act: -0.1700

Data Index: 3570669 (Open Web Text)

Max Activating Token Index: 306

Text #1

Max Range: 4.7925. Min Range: -4.7925

Max Act: 4.6812. Min Act: -0.1700

Data Index: 6263052 (Open Web Text)

Max Activating Token Index: 469

Text #2

Max Range: 4.7925. Min Range: -4.7925

Max Act: 4.6673. Min Act: -0.1700

Data Index: 4002747 (Open Web Text)

Max Activating Token Index: 583

Text #3

Max Range: 4.7925. Min Range: -4.7925

Max Act: 4.6052. Min Act: -0.1700

Data Index: 7359500 (Open Web Text)

Max Activating Token Index: 805

Text #4

Max Range: 4.7925. Min Range: -4.7925

Max Act: 4.6112. Min Act: -0.1700

Data Index: 7632098 (Open Web Text)

Max Activating Token Index: 363

Text #5

Max Range: 4.7925. Min Range: -4.7925

Max Act: 4.6077. Min Act: -0.1700

Data Index: 7442101 (Open Web Text)

Max Activating Token Index: 437

Text #6

Max Range: 4.7925. Min Range: -4.7925

Max Act: 4.5925. Min Act: -0.1700

Data Index: 536924 (Open Web Text)

Max Activating Token Index: 642

Text #7

Max Range: 4.7925. Min Range: -4.7925

Max Act: 4.4828. Min Act: -0.1700

Data Index: 807084 (Open Web Text)

Max Activating Token Index: 750

Text #8

Max Range: 4.7925. Min Range: -4.7925

Max Act: 4.5495. Min Act: -0.1700

Data Index: 1776578 (Open Web Text)

Max Activating Token Index: 686

Text #9

Max Range: 4.7925. Min Range: -4.7925

Max Act: 4.5629. Min Act: -0.1700

Data Index: 2754 (Open Web Text)

Max Activating Token Index: 1011

Text #10

Max Range: 4.7925. Min Range: -4.7925

Max Act: 4.5225. Min Act: -0.1700

Data Index: 5641516 (Open Web Text)

Max Activating Token Index: 188

Text #11

Max Range: 4.7925. Min Range: -4.7925

Max Act: 4.5569. Min Act: -0.1700

Data Index: 288641 (Open Web Text)

Max Activating Token Index: 273

Text #12

Max Range: 4.7925. Min Range: -4.7925

Max Act: 4.5500. Min Act: -0.1700

Data Index: 1821111 (Open Web Text)

Max Activating Token Index: 813

Text #13

Max Range: 4.7925. Min Range: -4.7925

Max Act: 4.5498. Min Act: -0.1700

Data Index: 3991819 (Open Web Text)

Max Activating Token Index: 476

Text #14

Max Range: 4.7925. Min Range: -4.7925

Max Act: 4.5057. Min Act: -0.1700

Data Index: 2554299 (Open Web Text)

Max Activating Token Index: 300

Text #15

Max Range: 4.7925. Min Range: -4.7925

Max Act: 4.5144. Min Act: -0.1700

Data Index: 7567215 (Open Web Text)

Max Activating Token Index: 342

Text #16

Max Range: 4.7925. Min Range: -4.7925

Max Act: 4.5067. Min Act: -0.1700

Data Index: 3883444 (Open Web Text)

Max Activating Token Index: 260

Text #17

Max Range: 4.7925. Min Range: -4.7925

Max Act: 4.5406. Min Act: -0.1700

Data Index: 5618565 (Open Web Text)

Max Activating Token Index: 835

Text #18

Max Range: 4.7925. Min Range: -4.7925

Max Act: 4.5468. Min Act: -0.1700

Data Index: 6995261 (Open Web Text)

Max Activating Token Index: 456

Text #19

Max Range: 4.7925. Min Range: -4.7925

Max Act: 4.5077. Min Act: -0.1700

Data Index: 2115973 (Open Web Text)

Max Activating Token Index: 451