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

Dataset: Open Web Text

Neuron 467 in Layer 5

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: 3.8011. Min Range: -3.8011

Max Act: 3.8011. Min Act: -0.1700

Data Index: 2750966 (Open Web Text)

Max Activating Token Index: 107

Text #1

Max Range: 3.8011. Min Range: -3.8011

Max Act: 3.6579. Min Act: -0.1700

Data Index: 4851683 (Open Web Text)

Max Activating Token Index: 942

Text #2

Max Range: 3.8011. Min Range: -3.8011

Max Act: 3.6500. Min Act: -0.1700

Data Index: 4174838 (Open Web Text)

Max Activating Token Index: 894

Text #3

Max Range: 3.8011. Min Range: -3.8011

Max Act: 3.6180. Min Act: -0.1700

Data Index: 1195604 (Open Web Text)

Max Activating Token Index: 431

Text #4

Max Range: 3.8011. Min Range: -3.8011

Max Act: 3.6238. Min Act: -0.1700

Data Index: 4851682 (Open Web Text)

Max Activating Token Index: 825

Text #5

Max Range: 3.8011. Min Range: -3.8011

Max Act: 3.6177. Min Act: -0.1700

Data Index: 8664328 (Open Web Text)

Max Activating Token Index: 541

Text #6

Max Range: 3.8011. Min Range: -3.8011

Max Act: 3.5899. Min Act: -0.1700

Data Index: 2016147 (Open Web Text)

Max Activating Token Index: 790

Text #7

Max Range: 3.8011. Min Range: -3.8011

Max Act: 3.5729. Min Act: -0.1700

Data Index: 7657775 (Open Web Text)

Max Activating Token Index: 547

Text #8

Max Range: 3.8011. Min Range: -3.8011

Max Act: 3.5815. Min Act: -0.1700

Data Index: 4197373 (Open Web Text)

Max Activating Token Index: 664

Text #9

Max Range: 3.8011. Min Range: -3.8011

Max Act: 3.5362. Min Act: -0.1700

Data Index: 2954941 (Open Web Text)

Max Activating Token Index: 365

Text #10

Max Range: 3.8011. Min Range: -3.8011

Max Act: 3.4905. Min Act: -0.1700

Data Index: 5387011 (Open Web Text)

Max Activating Token Index: 615

Text #11

Max Range: 3.8011. Min Range: -3.8011

Max Act: 3.5243. Min Act: -0.1700

Data Index: 5010333 (Open Web Text)

Max Activating Token Index: 474

Text #12

Max Range: 3.8011. Min Range: -3.8011

Max Act: 3.4710. Min Act: -0.1700

Data Index: 7567563 (Open Web Text)

Max Activating Token Index: 511

Text #13

Max Range: 3.8011. Min Range: -3.8011

Max Act: 3.4822. Min Act: -0.1700

Data Index: 7353275 (Open Web Text)

Max Activating Token Index: 1013

Text #14

Max Range: 3.8011. Min Range: -3.8011

Max Act: 3.4916. Min Act: -0.1700

Data Index: 551531 (Open Web Text)

Max Activating Token Index: 1005

Text #15

Max Range: 3.8011. Min Range: -3.8011

Max Act: 3.4421. Min Act: -0.1700

Data Index: 4895766 (Open Web Text)

Max Activating Token Index: 928

Text #16

Max Range: 3.8011. Min Range: -3.8011

Max Act: 3.4816. Min Act: -0.1700

Data Index: 3455988 (Open Web Text)

Max Activating Token Index: 729

Text #17

Max Range: 3.8011. Min Range: -3.8011

Max Act: 3.4523. Min Act: -0.1700

Data Index: 1950210 (Open Web Text)

Max Activating Token Index: 520

Text #18

Max Range: 3.8011. Min Range: -3.8011

Max Act: 3.4485. Min Act: -0.1700

Data Index: 2675944 (Open Web Text)

Max Activating Token Index: 533

Text #19

Max Range: 3.8011. Min Range: -3.8011

Max Act: 3.4590. Min Act: -0.1700

Data Index: 7957230 (Open Web Text)

Max Activating Token Index: 966