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

Dataset: Open Web Text

Neuron 677 in Layer 6

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: 3.0624. Min Range: -3.0624

Max Act: 3.0624. Min Act: -0.1700

Data Index: 7068399 (Open Web Text)

Max Activating Token Index: 708

Text #1

Max Range: 3.0624. Min Range: -3.0624

Max Act: 3.0400. Min Act: -0.1700

Data Index: 4978584 (Open Web Text)

Max Activating Token Index: 501

Text #2

Max Range: 3.0624. Min Range: -3.0624

Max Act: 3.0262. Min Act: -0.1700

Data Index: 3522261 (Open Web Text)

Max Activating Token Index: 350

Text #3

Max Range: 3.0624. Min Range: -3.0624

Max Act: 3.0255. Min Act: -0.1700

Data Index: 5048348 (Open Web Text)

Max Activating Token Index: 450

Text #4

Max Range: 3.0624. Min Range: -3.0624

Max Act: 3.0093. Min Act: -0.1700

Data Index: 2910250 (Open Web Text)

Max Activating Token Index: 848

Text #5

Max Range: 3.0624. Min Range: -3.0624

Max Act: 3.0054. Min Act: -0.1700

Data Index: 172266 (Open Web Text)

Max Activating Token Index: 607

Text #6

Max Range: 3.0624. Min Range: -3.0624

Max Act: 3.0227. Min Act: -0.1700

Data Index: 6988968 (Open Web Text)

Max Activating Token Index: 911

Text #7

Max Range: 3.0624. Min Range: -3.0624

Max Act: 2.9813. Min Act: -0.1700

Data Index: 4978582 (Open Web Text)

Max Activating Token Index: 853

Text #8

Max Range: 3.0624. Min Range: -3.0624

Max Act: 2.9761. Min Act: -0.1700

Data Index: 1821091 (Open Web Text)

Max Activating Token Index: 966

Text #9

Max Range: 3.0624. Min Range: -3.0624

Max Act: 2.9693. Min Act: -0.1700

Data Index: 8243927 (Open Web Text)

Max Activating Token Index: 691

Text #10

Max Range: 3.0624. Min Range: -3.0624

Max Act: 2.9653. Min Act: -0.1700

Data Index: 2910251 (Open Web Text)

Max Activating Token Index: 117

Text #11

Max Range: 3.0624. Min Range: -3.0624

Max Act: 2.9498. Min Act: -0.1700

Data Index: 7068407 (Open Web Text)

Max Activating Token Index: 388

Text #12

Max Range: 3.0624. Min Range: -3.0624

Max Act: 2.9455. Min Act: -0.1700

Data Index: 7068408 (Open Web Text)

Max Activating Token Index: 337

Text #13

Max Range: 3.0624. Min Range: -3.0624

Max Act: 2.9548. Min Act: -0.1700

Data Index: 6988967 (Open Web Text)

Max Activating Token Index: 976

Text #14

Max Range: 3.0624. Min Range: -3.0624

Max Act: 2.9448. Min Act: -0.1700

Data Index: 8243928 (Open Web Text)

Max Activating Token Index: 704

Text #15

Max Range: 3.0624. Min Range: -3.0624

Max Act: 2.9501. Min Act: -0.1700

Data Index: 4978583 (Open Web Text)

Max Activating Token Index: 653

Text #16

Max Range: 3.0624. Min Range: -3.0624

Max Act: 2.9339. Min Act: -0.1700

Data Index: 6842110 (Open Web Text)

Max Activating Token Index: 935

Text #17

Max Range: 3.0624. Min Range: -3.0624

Max Act: 2.9128. Min Act: -0.1700

Data Index: 8375367 (Open Web Text)

Max Activating Token Index: 1008

Text #18

Max Range: 3.0624. Min Range: -3.0624

Max Act: 2.9441. Min Act: -0.1700

Data Index: 2202366 (Open Web Text)

Max Activating Token Index: 793

Text #19

Max Range: 3.0624. Min Range: -3.0624

Max Act: 2.9280. Min Act: -0.1700

Data Index: 7068405 (Open Web Text)

Max Activating Token Index: 669