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

Dataset: Open Web Text

Neuron 851 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: 3.0637. Min Range: -3.0637

Max Act: 3.0637. Min Act: -0.1700

Data Index: 8314664 (Open Web Text)

Max Activating Token Index: 669

Text #1

Max Range: 3.0637. Min Range: -3.0637

Max Act: 2.9113. Min Act: -0.1700

Data Index: 3916175 (Open Web Text)

Max Activating Token Index: 657

Text #2

Max Range: 3.0637. Min Range: -3.0637

Max Act: 2.8038. Min Act: -0.1700

Data Index: 4215841 (Open Web Text)

Max Activating Token Index: 569

Text #3

Max Range: 3.0637. Min Range: -3.0637

Max Act: 2.8141. Min Act: -0.1700

Data Index: 831665 (Open Web Text)

Max Activating Token Index: 633

Text #4

Max Range: 3.0637. Min Range: -3.0637

Max Act: 2.8147. Min Act: -0.1700

Data Index: 7564588 (Open Web Text)

Max Activating Token Index: 392

Text #5

Max Range: 3.0637. Min Range: -3.0637

Max Act: 2.7937. Min Act: -0.1700

Data Index: 7771933 (Open Web Text)

Max Activating Token Index: 779

Text #6

Max Range: 3.0637. Min Range: -3.0637

Max Act: 2.8050. Min Act: -0.1700

Data Index: 6971591 (Open Web Text)

Max Activating Token Index: 456

Text #7

Max Range: 3.0637. Min Range: -3.0637

Max Act: 2.7713. Min Act: -0.1700

Data Index: 5873350 (Open Web Text)

Max Activating Token Index: 411

Text #8

Max Range: 3.0637. Min Range: -3.0637

Max Act: 2.7575. Min Act: -0.1700

Data Index: 4647668 (Open Web Text)

Max Activating Token Index: 76

Text #9

Max Range: 3.0637. Min Range: -3.0637

Max Act: 2.7575. Min Act: -0.1700

Data Index: 8266305 (Open Web Text)

Max Activating Token Index: 631

Text #10

Max Range: 3.0637. Min Range: -3.0637

Max Act: 2.7568. Min Act: -0.1700

Data Index: 6011503 (Open Web Text)

Max Activating Token Index: 497

Text #11

Max Range: 3.0637. Min Range: -3.0637

Max Act: 2.7480. Min Act: -0.1700

Data Index: 6895069 (Open Web Text)

Max Activating Token Index: 650

Text #12

Max Range: 3.0637. Min Range: -3.0637

Max Act: 2.7258. Min Act: -0.1700

Data Index: 4959571 (Open Web Text)

Max Activating Token Index: 204

Text #13

Max Range: 3.0637. Min Range: -3.0637

Max Act: 2.7439. Min Act: -0.1700

Data Index: 7991475 (Open Web Text)

Max Activating Token Index: 527

Text #14

Max Range: 3.0637. Min Range: -3.0637

Max Act: 2.7210. Min Act: -0.1700

Data Index: 339867 (Open Web Text)

Max Activating Token Index: 957

Text #15

Max Range: 3.0637. Min Range: -3.0637

Max Act: 2.6919. Min Act: -0.1700

Data Index: 905167 (Open Web Text)

Max Activating Token Index: 734

Text #16

Max Range: 3.0637. Min Range: -3.0637

Max Act: 2.6990. Min Act: -0.1700

Data Index: 3521823 (Open Web Text)

Max Activating Token Index: 132

Text #17

Max Range: 3.0637. Min Range: -3.0637

Max Act: 2.7041. Min Act: -0.1700

Data Index: 5593552 (Open Web Text)

Max Activating Token Index: 767

Text #18

Max Range: 3.0637. Min Range: -3.0637

Max Act: 2.6937. Min Act: -0.1700

Data Index: 7291995 (Open Web Text)

Max Activating Token Index: 999

Text #19

Max Range: 3.0637. Min Range: -3.0637

Max Act: 2.7045. Min Act: -0.1700

Data Index: 2619084 (Open Web Text)

Max Activating Token Index: 212